agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH 2/5] Move IS [NOT] NULL handling from BRIN support functions 286+ messages / 7 participants [nested] [flat]
* [PATCH 2/5] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-12 13:07 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-12 13:07 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit, and it simplifies the support procedures quite a bit, as they don't need to care about NULL values and flags at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 287 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +-------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 235 insertions(+), 264 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index ccf609e799..83c71d0f8e 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -359,6 +337,7 @@ brinbeginscan(Relation r, int nkeys, int norderbys) return scan; } + /* * Execute the index scan. * @@ -389,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -552,6 +551,45 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +732,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +760,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1540,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1626,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 853727190c..f5eaef416f 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -574,37 +506,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index a3bb3558ec..a625ef7aac 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 9ffc9100c0..7c4f3da0a0 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.25.4 --c7tltgiw2u7hovas Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="0003-BRIN-bloom-indexes-20200912.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-12 13:07 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-12 13:07 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit, and it simplifies the support procedures quite a bit, as they don't need to care about NULL values and flags at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 294 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 240 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index ccf609e799..f438e59c75 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -359,6 +337,7 @@ brinbeginscan(Relation r, int nkeys, int norderbys) return scan; } + /* * Execute the index scan. * @@ -389,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 853727190c..f5eaef416f 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -574,37 +506,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index a3bb3558ec..a625ef7aac 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 9ffc9100c0..7c4f3da0a0 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.25.4 --7kiiugxvbzvpnhzt Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="0003-optimize-allocations-20200913.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index ccf609e799..4dd29c7b10 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index b1b3ce700d..cb4eb438d3 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index b233558310..8886ad984e 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 9ffc9100c0..7c4f3da0a0 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------45196B023835614BDFCBD16D Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20201220.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20201220.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit, and it simplifies the support procedures quite a bit, as they don't need to care about NULL values and flags at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 294 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 240 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index ccf609e799..f438e59c75 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -359,6 +337,7 @@ brinbeginscan(Relation r, int nkeys, int norderbys) return scan; } + /* * Execute the index scan. * @@ -389,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 853727190c..f5eaef416f 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -574,37 +506,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index b233558310..8886ad984e 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 9ffc9100c0..7c4f3da0a0 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.25.4 --oygwhy5yjes6547y Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="0003-optimize-allocations-20200917.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit, and it simplifies the support procedures quite a bit, as they don't need to care about NULL values and flags at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 294 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 240 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index ccf609e799..f438e59c75 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -359,6 +337,7 @@ brinbeginscan(Relation r, int nkeys, int norderbys) return scan; } + /* * Execute the index scan. * @@ -389,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 853727190c..f5eaef416f 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -574,37 +506,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index b233558310..8886ad984e 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 9ffc9100c0..7c4f3da0a0 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.25.4 --5fmiyix6rzr5abmj Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="0003-optimize-allocations-20200917b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/7] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit, and it simplifies the support procedures quite a bit, as they don't need to care about NULL values and flags at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 294 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 240 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index ccf609e799..f438e59c75 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -359,6 +337,7 @@ brinbeginscan(Relation r, int nkeys, int norderbys) return scan; } + /* * Execute the index scan. * @@ -389,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 853727190c..f5eaef416f 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -574,37 +506,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index b233558310..8886ad984e 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 9ffc9100c0..7c4f3da0a0 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --zzslo7zt7tqdcawh Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="0003-optimize-allocations-20201103.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index ccf609e799..4dd29c7b10 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 853727190c..f5eaef416f 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -574,37 +506,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index b233558310..8886ad984e 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 9ffc9100c0..7c4f3da0a0 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------90362739C57C6315B5637FAD Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20201107.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20201107.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index ccf609e799..4dd29c7b10 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 853727190c..f5eaef416f 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -574,37 +506,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index b233558310..8886ad984e 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 9ffc9100c0..7c4f3da0a0 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------291E0481B4400C0ECC8E497A Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20201108.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20201108.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------4B194FF8F3EA3786FF9EAE1F Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210203.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------0E72B707603BED22B4040825 Content-Type: text/x-patch; charset=UTF-8; name="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0001-Pass-all-scan-keys-to-BRIN-consistent-funct-20210211.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------22A4B241170149838D4D1F8F Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210215.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------CF71AF65F7C337C37C24B045 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210112.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 8a1a9da78f..55851376d8 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -178,7 +181,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -242,31 +244,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -389,8 +367,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -415,10 +395,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -439,23 +422,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -463,9 +447,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -543,15 +541,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -694,7 +734,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -723,25 +762,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1520,6 +1542,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1573,3 +1628,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 85c612e490..7b79a52536 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D21F32E0F9E7408E9BE1AF2E Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------310A2AE1CC4C2E2E77559E3D Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210114-2.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions @ 2020-09-17 15:26 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2020-09-17 15:26 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 106 +------- src/backend/access/brin/brin_minmax.c | 103 +------- src/include/access/brin_internal.h | 3 + 4 files changed, 239 insertions(+), 266 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index dc187153aa..14da9ed17f 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -416,10 +396,13 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) /* * Make room for per-attribute lists of scan keys that we'll pass to the - * consistent support procedure. + * consistent support procedure. We keep null and regular keys separate, + * so that we can easily pass regular keys to the consistent function. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -440,23 +423,24 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno-1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan + * keys are there for a given attribute, so we simply allocate + * the largest number possible (as if all scan keys belonged to + * the same attribute). This may waste a bit of memory, but we + * only expect small number of scan keys in general, so this + * should be negligible, and it's probably cheaper than having + * to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many - * scan keys are there for this attribute, so we simply - * allocate the largest number possible. This may waste - * a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, - * and it's cheaper than having to repalloc repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -464,9 +448,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -544,15 +542,57 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular + * and IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine mismatch + * within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all passed. + * If there are no regular scan keys, we're done - the page + * range matches. If there are regular keys, but the page + * range is marked as 'all nulls' it can't possibly pass + * (we're assuming the operators are strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -695,7 +735,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -724,25 +763,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1521,6 +1543,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1574,3 +1629,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; + * our deformed tuple will get updated if the new tuple doesn't fit + * the original range (note this means we can't break out of the loop + * early). Make a note of whether this happens, so that we know to + * insert the modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's + * the first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to + * have only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index 215bc794d3..f4730be3b9 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -264,63 +254,6 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* It has to be checked, if it contains elements that are not mergeable. */ if (DatumGetBool(column->bv_values[INCLUSION_UNMERGEABLE])) @@ -331,9 +264,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -572,37 +504,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index 12878ff3a0..6c8852d404 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -152,72 +142,14 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool regular_keys = false; - - /* - * First check if there are any IS NULL scan keys, and if we're - * violating them. In that case we can terminate early, without - * inspecting the ranges. - */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* handle IS NULL/IS NOT NULL tests */ - if (key->sk_flags & SK_ISNULL) - { - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - else - /* note we have regular (non-NULL) scan keys */ - regular_keys = true; - } - - /* - * If the page range is all nulls, it cannot possibly be consistent if - * there are some regular scan keys. - */ - if (column->bv_allnulls && regular_keys) - PG_RETURN_BOOL(false); - - /* If there are no regular keys, the page range is considered consistent. */ - if (!regular_keys) - PG_RETURN_BOOL(true); /* Check that the range is consistent with all scan keys. */ for (keyno = 0; keyno < nkeys; keyno++) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the @@ -308,34 +240,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------FA974B75A0C3E9CA18CE7207 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210122.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------AC3FFB734F56C5F52D422EFC Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210305.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------82D677E9F94AC7574E460205 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 743f2a925a..ce0f525c21 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -550,15 +549,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -665,7 +707,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -694,25 +735,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1491,6 +1515,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1544,3 +1601,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------D524CD37E77B36A2883A7617 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210311.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index f9a0476024..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------556A1DC61262AF15641DB204 Content-Type: text/x-patch; charset=UTF-8; name="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0005-Optimize-allocations-in-bringetbitmap-20210308b.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-21 23:24 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-21 23:24 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Nikita Glukhov <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 33f4e2c15c..efda84aba3 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -420,13 +400,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * keys, so we allocate space for all attributes. That may use more memory * but it's probably cheaper than determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest index can have 32 attributes, so the amount of wasted * memory is negligible. We could invent a more compact approach (with * just space for used attributes) but that would make the matching more * complex so it's not a good trade-off. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* Preprocess the scan keys - split them into per-attribute arrays. */ for (keyno = 0; keyno < scan->numberOfKeys; keyno++) @@ -444,23 +429,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this attribute, so init the array of keys. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for this attribute, so we simply allocate the largest number + * possible (as if all keys were for this attribute). This may waste a + * bit of memory, but we only expect small number of scan keys in + * general, so this should be negligible, and repeated repalloc calls + * are not free either. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible (as if all keys were for this attribute). This - * may waste a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, and - * repeated repalloc calls are not free either. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -468,9 +453,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -663,7 +705,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -692,25 +733,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1489,6 +1513,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1542,3 +1599,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index cf2d029048..d8cfc9d909 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.30.2 --------------76348C5C2C314FA585652FE5 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210322.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210322.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-21 23:24 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: Tomas Vondra @ 2021-03-21 23:24 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Nikita Glukhov <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 33f4e2c15c..efda84aba3 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -420,13 +400,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * keys, so we allocate space for all attributes. That may use more memory * but it's probably cheaper than determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest index can have 32 attributes, so the amount of wasted * memory is negligible. We could invent a more compact approach (with * just space for used attributes) but that would make the matching more * complex so it's not a good trade-off. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* Preprocess the scan keys - split them into per-attribute arrays. */ for (keyno = 0; keyno < scan->numberOfKeys; keyno++) @@ -444,23 +429,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this attribute, so init the array of keys. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for this attribute, so we simply allocate the largest number + * possible (as if all keys were for this attribute). This may waste a + * bit of memory, but we only expect small number of scan keys in + * general, so this should be negligible, and repeated repalloc calls + * are not free either. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible (as if all keys were for this attribute). This - * may waste a bit of memory, but we only expect small number of - * scan keys in general, so this should be negligible, and - * repeated repalloc calls are not free either. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -468,9 +453,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) Datum add; Oid collation; - /* skip attributes without any scan keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -663,7 +705,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -692,25 +733,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1489,6 +1513,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1542,3 +1599,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index cf2d029048..d8cfc9d909 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.30.2 --------------76348C5C2C314FA585652FE5 Content-Type: text/x-patch; charset=UTF-8; name="0004-Optimize-allocations-in-bringetbitmap-20210322.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0004-Optimize-allocations-in-bringetbitmap-20210322.patch" ^ permalink raw reply [nested|flat] 286+ messages in thread
* Shave a few cycles off our ilog10 implementation @ 2024-10-30 19:27 David Fetter <[email protected]> 0 siblings, 1 reply; 286+ messages in thread From: David Fetter @ 2024-10-30 19:27 UTC (permalink / raw) To: pgsql-hackers Please find attached a patch to $Subject I've done some preliminary testing, and it appears to shave somewhere between 25-50% off the operations themselves, and these cascade into things like formatting result sets and COPY OUT. Best, David. -- David Fetter <david(at)fetter(dot)org> http://fetter.org/ Phone: +1 415 235 3778 ^ permalink raw reply [nested|flat] 286+ messages in thread
* Re: Shave a few cycles off our ilog10 implementation @ 2024-10-30 19:54 Heikki Linnakangas <[email protected]> parent: David Fetter <[email protected]> 0 siblings, 1 reply; 286+ messages in thread From: Heikki Linnakangas @ 2024-10-30 19:54 UTC (permalink / raw) To: David Fetter <[email protected]>; pgsql-hackers On 30/10/2024 21:27, David Fetter wrote: > Please find attached a patch to $Subject > > I've done some preliminary testing, and it appears to shave somewhere > between 25-50% off the operations themselves, and these cascade into > things like formatting result sets and COPY OUT. Impressive! What did you use to performance test it, to get those results? -- Heikki Linnakangas Neon (https://neon.tech) ^ permalink raw reply [nested|flat] 286+ messages in thread
* Re: Shave a few cycles off our ilog10 implementation @ 2024-10-30 20:02 David Fetter <[email protected]> parent: Heikki Linnakangas <[email protected]> 0 siblings, 1 reply; 286+ messages in thread From: David Fetter @ 2024-10-30 20:02 UTC (permalink / raw) To: Heikki Linnakangas <[email protected]>; +Cc: pgsql-hackers On Wed, Oct 30, 2024 at 09:54:20PM +0200, Heikki Linnakangas wrote: > On 30/10/2024 21:27, David Fetter wrote: > > Please find attached a patch to $Subject > > > > I've done some preliminary testing, and it appears to shave somewhere > > between 25-50% off the operations themselves, and these cascade into > > things like formatting result sets and COPY OUT. > > Impressive! What did you use to performance test it, to get those results? In case that wasn't clear, what I've tested so far was the ilog10 implementations, not the general effects on the things they underlie. This testing was basically just sending a bunch of appropriately sized pseudo-random uints in a previously created array sent through a tight loop that called the ilog10s and getting average execution times. Any suggestions for more thorough testing would be welcome. Best, David. -- David Fetter <david(at)fetter(dot)org> http://fetter.org/ Phone: +1 415 235 3778 ^ permalink raw reply [nested|flat] 286+ messages in thread
* Re: Shave a few cycles off our ilog10 implementation @ 2024-10-30 20:14 David Rowley <[email protected]> parent: David Fetter <[email protected]> 0 siblings, 1 reply; 286+ messages in thread From: David Rowley @ 2024-10-30 20:14 UTC (permalink / raw) To: David Fetter <[email protected]>; +Cc: Heikki Linnakangas <[email protected]>; pgsql-hackers On Thu, 31 Oct 2024 at 09:02, David Fetter <[email protected]> wrote: > This testing was basically just sending a bunch of appropriately sized > pseudo-random uints in a previously created array sent through a tight > loop that called the ilog10s and getting average execution times. > > Any suggestions for more thorough testing would be welcome. Maybe something similar to what I did in [1]. David [1] https://postgr.es/m/CAApHDvopR=yPgNr4AbbN4HMOztuyVa+iFYRTvu49pxg9YO_tKw@mail.gmail.com ^ permalink raw reply [nested|flat] 286+ messages in thread
* Re: Shave a few cycles off our ilog10 implementation @ 2024-12-18 10:42 John Naylor <[email protected]> parent: David Rowley <[email protected]> 0 siblings, 1 reply; 286+ messages in thread From: John Naylor @ 2024-12-18 10:42 UTC (permalink / raw) To: David Rowley <[email protected]>; +Cc: David Fetter <[email protected]>; Heikki Linnakangas <[email protected]>; pgsql-hackers On Thu, Oct 31, 2024 at 3:14 AM David Rowley <[email protected]> wrote: > > On Thu, 31 Oct 2024 at 09:02, David Fetter <[email protected]> wrote: > > This testing was basically just sending a bunch of appropriately sized > > pseudo-random uints in a previously created array sent through a tight > > loop that called the ilog10s and getting average execution times. > > > > Any suggestions for more thorough testing would be welcome. > > Maybe something similar to what I did in [1]. > > David > > [1] https://postgr.es/m/CAApHDvopR=yPgNr4AbbN4HMOztuyVa+iFYRTvu49pxg9YO_tKw@mail.gmail.com I tried this test as-is and saw no difference. I bumped it up to 10 columns and got (no turbo, about 30 transactions): master: 6831.308 ms patch: 6580.506 ms The difference is small enough that normally I'd say it's likely unrelated to the patch, but on the other hand it's consistent with saving (3 * 10 * 10 million) cycles because of 1 less multiplication each, which is not nothing, but for shoving bytes into /dev/null it's not exciting either. The lookup for the 64-bit case has grown to 1024 bytes, which will compete for cache space. I don't have a strong reason to be either for or against this patch. Anyone else want to test? create table bi (a bigint, b bigint, c bigint, d bigint, e bigint, f bigint, g bigint, h bigint, i bigint, j bigint); insert into bi select i,i,i,i,i,i,i,i,i,i from generate_Series(1,10_000_000) i; vacuum freeze analyze bi; pgbench -n -T 180 -f bench.sql -- John Naylor Amazon Web Services ^ permalink raw reply [nested|flat] 286+ messages in thread
* Re: Shave a few cycles off our ilog10 implementation @ 2024-12-19 03:30 David Rowley <[email protected]> parent: John Naylor <[email protected]> 0 siblings, 0 replies; 286+ messages in thread From: David Rowley @ 2024-12-19 03:30 UTC (permalink / raw) To: John Naylor <[email protected]>; +Cc: David Fetter <[email protected]>; Heikki Linnakangas <[email protected]>; pgsql-hackers On Wed, 18 Dec 2024 at 23:42, John Naylor <[email protected]> wrote: > The difference is small enough that normally I'd say it's likely > unrelated to the patch, but on the other hand it's consistent with > saving (3 * 10 * 10 million) cycles because of 1 less multiplication > each, which is not nothing, but for shoving bytes into /dev/null it's > not exciting either. The lookup for the 64-bit case has grown to 1024 > bytes, which will compete for cache space. I don't have a strong > reason to be either for or against this patch. Anyone else want to > test? I tried it out too on my Zen4 machine. I don't doubt David saw a speedup when testing the performance in isolation, but I can't detect anything going faster when using it in Postgres. Maybe we can revisit if we make COPY TO faster someday. As of today, it's a pretty inefficient lump of code. My results: $ echo master && ./intbench.sh master NOTICE: relation "tmp" already exists, skipping CREATE TABLE AS latency average = 246.294 ms latency average = 243.167 ms latency average = 245.620 ms latency average = 247.135 ms latency average = 248.206 ms latency average = 253.433 ms latency average = 259.296 ms latency average = 248.856 ms latency average = 247.518 ms latency average = 259.581 ms latency average = 244.426 ms latency average = 244.553 ms latency average = 249.909 ms latency average = 244.079 ms latency average = 246.422 ms latency average = 248.763 ms latency average = 247.318 ms latency average = 249.675 ms latency average = 245.192 ms latency average = 253.975 ms $ echo patched && ./intbench.sh patched NOTICE: relation "tmp" already exists, skipping CREATE TABLE AS latency average = 253.964 ms latency average = 257.463 ms latency average = 250.506 ms latency average = 252.401 ms latency average = 260.806 ms latency average = 250.120 ms latency average = 251.539 ms latency average = 262.180 ms latency average = 252.349 ms latency average = 251.332 ms latency average = 249.490 ms latency average = 252.696 ms latency average = 251.895 ms latency average = 248.466 ms latency average = 255.839 ms latency average = 253.334 ms latency average = 250.548 ms latency average = 288.164 ms latency average = 252.587 ms latency average = 256.059 ms perf top: master: 16.59% postgres [.] CopyAttributeOutText 15.63% libc.so.6 [.] __memmove_avx512_unaligned_erms 12.94% postgres [.] pg_ltoa 9.85% postgres [.] CopyOneRowTo 6.86% postgres [.] AllocSetAlloc 6.73% postgres [.] tts_buffer_heap_getsomeattrs patched 19.53% libc.so.6 [.] __memmove_avx512_unaligned_erms 12.52% postgres [.] pg_ltoa 11.76% postgres [.] CopyAttributeOutText 11.40% postgres [.] CopyOneRowTo 6.96% postgres [.] tts_buffer_heap_getsomeattrs 6.35% postgres [.] AllocSetAlloc I can't think of what we have that exercises pg_ltoa() or pg_ultoa_n() more. timestamp_out() might, but that's lots of small ints. David #!/bin/bash dbname=postgres psql -c "create table if not exists tmp as select random(1,1e9) c1, random(1,1e9) c2,random(1,1e9) c3,random(1,1e9) c4,random(1,1e9) c5,random(1,1e9) c6,random(1,1e9) c7,random(1,1e9) c8,random(1,1e9) c9,random(1,1e9) c10 from generate_series(1,1000000);" $dbname for i in {1..20} do sleep 10 echo "copy tmp to '/dev/null'" > bench.sql pgbench -n -f bench.sql -T 10 $dbname | grep latency done; Attachments: [text/plain] intbench.sh.txt (429B, ../../CAApHDvqQT98yVqXsxY40=rp_XYv4dhzFn85s6yrVwwi46c+TWg@mail.gmail.com/2-intbench.sh.txt) download | inline: #!/bin/bash dbname=postgres psql -c "create table if not exists tmp as select random(1,1e9) c1, random(1,1e9) c2,random(1,1e9) c3,random(1,1e9) c4,random(1,1e9) c5,random(1,1e9) c6,random(1,1e9) c7,random(1,1e9) c8,random(1,1e9) c9,random(1,1e9) c10 from generate_series(1,1000000);" $dbname for i in {1..20} do sleep 10 echo "copy tmp to '/dev/null'" > bench.sql pgbench -n -f bench.sql -T 10 $dbname | grep latency done; ^ permalink raw reply [nested|flat] 286+ messages in thread
end of thread, other threads:[~2024-12-19 03:30 UTC | newest] Thread overview: 286+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2020-09-12 13:07 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-12 13:07 [PATCH 2/5] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/7] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/9] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2020-09-17 15:26 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 4/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-21 23:24 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2021-03-21 23:24 [PATCH 3/8] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2024-10-30 19:27 Shave a few cycles off our ilog10 implementation David Fetter <[email protected]> 2024-10-30 19:54 ` Re: Shave a few cycles off our ilog10 implementation Heikki Linnakangas <[email protected]> 2024-10-30 20:02 ` Re: Shave a few cycles off our ilog10 implementation David Fetter <[email protected]> 2024-10-30 20:14 ` Re: Shave a few cycles off our ilog10 implementation David Rowley <[email protected]> 2024-12-18 10:42 ` Re: Shave a few cycles off our ilog10 implementation John Naylor <[email protected]> 2024-12-19 03:30 ` Re: Shave a few cycles off our ilog10 implementation David Rowley <[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