agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v43 1/2] Subscripting for jsonb
259+ messages / 2 participants
[nested] [flat]

* [PATCH v43 1/2] Subscripting for jsonb
@ 2020-12-18 16:19  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 259+ messages in thread

From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw)

Subscripting implementation for jsonb. It does not support slices, does
not have a limit for number of subscripts and for assignment expects a
replace value to be of jsonb type. There is also one functional
difference in assignment via subscripting from jsonb_set, when an
original jsonb container is NULL, subscripting replaces it with an empty
jsonb and proceed with assignment.

For the sake of code reuse, some parts of jsonb functionality were
rearranged to allow use the same functions for jsonb_set and assign
subscripting operation.

The original idea belongs to Oleg Bartunov.

Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule
---
 doc/src/sgml/json.sgml              |  48 ++++
 src/backend/utils/adt/Makefile      |   1 +
 src/backend/utils/adt/jsonb_util.c  |  76 ++++-
 src/backend/utils/adt/jsonbsubs.c   | 413 ++++++++++++++++++++++++++++
 src/backend/utils/adt/jsonfuncs.c   | 180 ++++++------
 src/include/catalog/pg_proc.dat     |   4 +
 src/include/catalog/pg_type.dat     |   3 +-
 src/include/utils/jsonb.h           |   6 +-
 src/test/regress/expected/jsonb.out | 272 +++++++++++++++++-
 src/test/regress/sql/jsonb.sql      |  84 +++++-
 10 files changed, 982 insertions(+), 105 deletions(-)
 create mode 100644 src/backend/utils/adt/jsonbsubs.c

diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml
index 5b9a5557a4..100d1a60f4 100644
--- a/doc/src/sgml/json.sgml
+++ b/doc/src/sgml/json.sgml
@@ -602,6 +602,54 @@ SELECT jdoc-&gt;'guid', jdoc-&gt;'name' FROM api WHERE jdoc @&gt; '{"tags": ["qu
   </para>
  </sect2>
 
+ <sect2 id="jsonb-subscripting">
+  <title><type>jsonb</type> Subscripting</title>
+  <para>
+   <type>jsonb</type> data type supports array-style subscripting expressions
+   to extract or update particular elements. It's possible to use multiple
+   subscripting expressions to extract nested values. In this case, a chain of
+   subscripting expressions follows the same rules as the
+   <literal>path</literal> argument in <literal>jsonb_set</literal> function,
+   e.g. in case of arrays it is a 0-based operation or that negative integers
+   that appear in <literal>path</literal> count from the end of JSON arrays.
+   The result of subscripting expressions is always jsonb data type. An
+   example of subscripting syntax:
+<programlisting>
+-- Extract value by key
+SELECT ('{"a": 1}'::jsonb)['a'];
+
+-- Extract nested value by key path
+SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c'];
+
+-- Extract element by index
+SELECT ('[1, "2", null]'::jsonb)[1];
+
+-- Update value by key, note the single quotes - the assigned value
+-- needs to be of jsonb type as well
+UPDATE table_name SET jsonb_field['key'] = '1';
+
+-- Select records using where clause with subscripting. Since the result of
+-- subscripting is jsonb and we basically want to compare two jsonb objects, we
+-- need to put the value in double quotes to be able to convert it to jsonb.
+SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"';
+</programlisting>
+
+  Subscripting for <type>jsonb</type> does not support slice expressions,
+  even if it contains an array.
+
+  In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment
+  via subscripting will proceed as if it was an empty JSON object:
+<programlisting>
+-- If jsonb_field here is NULL, the result is {"a": 1}
+UPDATE table_name SET jsonb_field['a'] = '1';
+
+-- If jsonb_field here is NULL, the result is [1]
+UPDATE table_name SET jsonb_field[0] = '1';
+</programlisting>
+
+  </para>
+ </sect2>
+
  <sect2>
   <title>Transforms</title>
 
diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile
index 82732146d3..279ff15ade 100644
--- a/src/backend/utils/adt/Makefile
+++ b/src/backend/utils/adt/Makefile
@@ -50,6 +50,7 @@ OBJS = \
 	jsonb_op.o \
 	jsonb_util.o \
 	jsonfuncs.o \
+	jsonbsubs.o \
 	jsonpath.o \
 	jsonpath_exec.o \
 	jsonpath_gram.o \
diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c
index 4eeffa1424..41a1c1f9bb 100644
--- a/src/backend/utils/adt/jsonb_util.c
+++ b/src/backend/utils/adt/jsonb_util.c
@@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate,
 										JsonbIteratorToken seq,
 										JsonbValue *scalarVal);
 
+JsonbValue *
+JsonbToJsonbValue(Jsonb *jsonb)
+{
+	JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue));
+
+	val->type = jbvBinary;
+	val->val.binary.data = &jsonb->root;
+	val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ;
+
+	return val;
+}
+
 /*
  * Turn an in-memory JsonbValue into a Jsonb for on-disk storage.
  *
- * There isn't a JsonbToJsonbValue(), because generally we find it more
- * convenient to directly iterate through the Jsonb representation and only
- * really convert nested scalar values.  JsonbIteratorNext() does this, so that
- * clients of the iteration code don't have to directly deal with the binary
- * representation (JsonbDeepContains() is a notable exception, although all
- * exceptions are internal to this module).  In general, functions that accept
- * a JsonbValue argument are concerned with the manipulation of scalar values,
- * or simple containers of scalar values, where it would be inconvenient to
- * deal with a great amount of other state.
+ * Generally we find it more convenient to directly iterate through the Jsonb
+ * representation and only really convert nested scalar values.
+ * JsonbIteratorNext() does this, so that clients of the iteration code don't
+ * have to directly deal with the binary representation (JsonbDeepContains() is
+ * a notable exception, although all exceptions are internal to this module).
+ * In general, functions that accept a JsonbValue argument are concerned with
+ * the manipulation of scalar values, or simple containers of scalar values,
+ * where it would be inconvenient to deal with a great amount of other state.
  */
 Jsonb *
 JsonbValueToJsonb(JsonbValue *val)
@@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq,
 	JsonbValue *res = NULL;
 	JsonbValue	v;
 	JsonbIteratorToken tok;
+	int	i;
+
+	if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject)
+	{
+		pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL);
+		for (i = 0; i < jbval->val.object.nPairs; i++)
+		{
+			pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key);
+			pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value);
+		}
+
+		return pushJsonbValue(pstate, WJB_END_OBJECT, NULL);
+	}
+
+	if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray)
+	{
+		pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL);
+		for (i = 0; i < jbval->val.array.nElems; i++)
+		{
+			pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]);
+		}
+
+		return pushJsonbValue(pstate, WJB_END_ARRAY, NULL);
+	}
 
 	if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) ||
 		jbval->type != jbvBinary)
@@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq,
 
 	/* unpack the binary and add each piece to the pstate */
 	it = JsonbIteratorInit(jbval->val.binary.data);
+
+	if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate)
+	{
+		tok = JsonbIteratorNext(&it, &v, true);
+		Assert(tok == WJB_BEGIN_ARRAY);
+		Assert(v.type == jbvArray && v.val.array.rawScalar);
+
+		tok = JsonbIteratorNext(&it, &v, true);
+		Assert(tok == WJB_ELEM);
+
+		res = pushJsonbValueScalar(pstate, seq, &v);
+
+		tok = JsonbIteratorNext(&it, &v, true);
+		Assert(tok == WJB_END_ARRAY);
+		Assert(it == NULL);
+
+		return res;
+	}
+
 	while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE)
 		res = pushJsonbValueScalar(pstate, tok,
-								   tok < WJB_BEGIN_ARRAY ? &v : NULL);
+								   tok < WJB_BEGIN_ARRAY ||
+								   (tok == WJB_BEGIN_ARRAY &&
+									v.val.array.rawScalar) ? &v : NULL);
 
 	return res;
 }
diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c
new file mode 100644
index 0000000000..306c37b5a6
--- /dev/null
+++ b/src/backend/utils/adt/jsonbsubs.c
@@ -0,0 +1,413 @@
+/*-------------------------------------------------------------------------
+ *
+ * jsonbsubs.c
+ *	  Subscripting support functions for jsonb.
+ *
+ * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/utils/adt/jsonbsubs.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "executor/execExpr.h"
+#include "nodes/makefuncs.h"
+#include "nodes/nodeFuncs.h"
+#include "nodes/subscripting.h"
+#include "parser/parse_coerce.h"
+#include "parser/parse_expr.h"
+#include "utils/jsonb.h"
+#include "utils/jsonfuncs.h"
+#include "utils/builtins.h"
+#include "utils/lsyscache.h"
+
+
+/* SubscriptingRefState.workspace for jsonb subscripting execution */
+typedef struct JsonbSubWorkspace
+{
+	bool		expectArray;	/* jsonb root is expected to be an array */
+	Oid		   *indexOid;		/* OID of coerced subscript expression,
+								   could be only integer or text */
+	Datum	   *index;			/* Subscript values in Datum format */
+} JsonbSubWorkspace;
+
+
+/*
+ * Finish parse analysis of a SubscriptingRef expression for a jsonb.
+ *
+ * Transform the subscript expressions, coerce them to text,
+ * and determine the result type of the SubscriptingRef node.
+ */
+static void
+jsonb_subscript_transform(SubscriptingRef *sbsref,
+						  List *indirection,
+						  ParseState *pstate,
+						  bool isSlice,
+						  bool isAssignment)
+{
+	List	   *upperIndexpr = NIL;
+	ListCell   *idx;
+
+	/*
+	 * Transform and convert the subscript expressions. Jsonb subscripting does
+	 * not support slices, look only and the upper index.
+	 */
+	foreach(idx, indirection)
+	{
+		A_Indices  *ai = lfirst_node(A_Indices, idx);
+		Node	   *subExpr;
+
+		if (isSlice)
+		{
+			Node	*expr = ai->uidx ? ai->uidx : ai->lidx;
+
+			ereport(ERROR,
+					(errcode(ERRCODE_DATATYPE_MISMATCH),
+					 errmsg("jsonb subscript does not support slices"),
+					 parser_errposition(pstate, exprLocation(expr))));
+		}
+
+		if (ai->uidx)
+		{
+			Oid subExprType = InvalidOid,
+				targetType = UNKNOWNOID;
+
+			subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind);
+			subExprType = exprType(subExpr);
+
+			if (subExprType != UNKNOWNOID)
+			{
+				Oid 	targets[2] = {INT4OID, TEXTOID};
+
+				/*
+				 * Jsonb can handle multiple subscript types, but cases when a
+				 * subscript could be coerced to multiple target types must be
+				 * avoided, similar to overloaded functions. It could be
+				 * possibly extend with jsonpath in the future.
+				 */
+				for (int i = 0; i < 2; i++)
+				{
+					if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT))
+					{
+						/*
+						 * One type has already succeeded, it means there are
+						 * two coercion targets possible, failure.
+						 */
+						if (targetType != UNKNOWNOID)
+							ereport(ERROR,
+									(errcode(ERRCODE_DATATYPE_MISMATCH),
+									 errmsg("subscript type is not supported"),
+									 errhint("Jsonb subscript must be coerced "
+											 "only to one type, integer or text."),
+									 parser_errposition(pstate, exprLocation(subExpr))));
+
+						targetType = targets[i];
+					}
+				}
+
+				/*
+				 * No suitable types were found, failure.
+				 */
+				if (targetType == UNKNOWNOID)
+					ereport(ERROR,
+							(errcode(ERRCODE_DATATYPE_MISMATCH),
+							 errmsg("subscript type is not supported"),
+							 errhint("Jsonb subscript must be coercet to either integer or text"),
+							 parser_errposition(pstate, exprLocation(subExpr))));
+			}
+			else
+				targetType = TEXTOID;
+
+			/*
+			 * We known from can_coerce_type that coercion will succeed, so
+			 * coerce_type could be used. Note the implicit coercion context,
+			 * which is required to handle subscripts of different types,
+			 * similar to overloaded functions.
+			 */
+			subExpr = coerce_type(pstate,
+								  subExpr, subExprType,
+								  targetType, -1,
+								  COERCION_IMPLICIT,
+								  COERCE_IMPLICIT_CAST,
+								  -1);
+			if (subExpr == NULL)
+				ereport(ERROR,
+						(errcode(ERRCODE_DATATYPE_MISMATCH),
+						 errmsg("jsonb subscript must have text type"),
+						 parser_errposition(pstate, exprLocation(subExpr))));
+		}
+		else
+		{
+			/*
+			 * Slice with omitted upper bound. Should not happen as we already
+			 * errored out on slice earlier, but handle this just in case.
+			 */
+			Assert(isSlice && ai->is_slice);
+			ereport(ERROR,
+					(errcode(ERRCODE_DATATYPE_MISMATCH),
+					 errmsg("jsonb subscript does not support slices"),
+					 parser_errposition(pstate, exprLocation(ai->uidx))));
+		}
+
+		upperIndexpr = lappend(upperIndexpr, subExpr);
+	}
+
+	/* store the transformed lists into the SubscriptRef node */
+	sbsref->refupperindexpr = upperIndexpr;
+	sbsref->reflowerindexpr = NIL;
+
+	/* Determine the result type of the subscripting operation; always jsonb */
+	sbsref->refrestype = JSONBOID;
+	sbsref->reftypmod = -1;
+}
+
+/*
+ * During execution, process the subscripts in a SubscriptingRef expression.
+ *
+ * The subscript expressions are already evaluated in Datum form in the
+ * SubscriptingRefState's arrays.  Check and convert them as necessary.
+ *
+ * If any subscript is NULL, we throw error in assignment cases, or in fetch
+ * cases set result to NULL and return false (instructing caller to skip the
+ * rest of the SubscriptingRef sequence).
+ */
+static bool
+jsonb_subscript_check_subscripts(ExprState *state,
+								 ExprEvalStep *op,
+								 ExprContext *econtext)
+{
+	SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state;
+	JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace;
+
+	/*
+	 * In case if the first subscript is an integer, the source jsonb is
+	 * expected to be an array. This information is not used directly, all such
+	 * cases are handled within corresponding jsonb assign functions. But if
+	 * the source jsonb is NULL the expected type will be used to construct an
+	 * empty source.
+	 */
+	if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] &&
+		!sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID)
+		workspace->expectArray = true;
+
+	/* Process upper subscripts */
+	for (int i = 0; i < sbsrefstate->numupper; i++)
+	{
+		if (sbsrefstate->upperprovided[i])
+		{
+			/* If any index expr yields NULL, result is NULL or error */
+			if (sbsrefstate->upperindexnull[i])
+			{
+				if (sbsrefstate->isassignment)
+					ereport(ERROR,
+							(errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED),
+							 errmsg("jsonb subscript in assignment must not be null")));
+				*op->resnull = true;
+				return false;
+			}
+
+			/*
+			 * For jsonb fetch and assign functions we need to provide path in
+			 * text format. Convert if it's not already text.
+			 */
+			if (workspace->indexOid[i] == INT4OID)
+			{
+				Datum	datum = sbsrefstate->upperindex[i];
+				char   *cs = DatumGetCString(DirectFunctionCall1(int4out, datum));
+				workspace->index[i] = CStringGetTextDatum(cs);
+			}
+			else
+				workspace->index[i] = sbsrefstate->upperindex[i];
+		}
+	}
+
+	return true;
+}
+
+/*
+ * Evaluate SubscriptingRef fetch for a jsonb element.
+ *
+ * Source container is in step's result variable (it's known not NULL, since
+ * we set fetch_strict to true).
+ */
+static void
+jsonb_subscript_fetch(ExprState *state,
+					  ExprEvalStep *op,
+					  ExprContext *econtext)
+{
+	SubscriptingRefState *sbsrefstate = op->d.sbsref.state;
+	JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace;
+	Jsonb		*jsonbSource;
+
+	/* Should not get here if source jsonb (or any subscript) is null */
+	Assert(!(*op->resnull));
+
+	jsonbSource = DatumGetJsonbP(*op->resvalue);
+	*op->resvalue = jsonb_get_element(jsonbSource,
+									  workspace->index,
+									  sbsrefstate->numupper,
+									  op->resnull,
+									  false);
+}
+
+/*
+ * Evaluate SubscriptingRef assignment for a jsonb element assignment.
+ *
+ * Input container (possibly null) is in result area, replacement value is in
+ * SubscriptingRefState's replacevalue/replacenull.
+ */
+static void
+jsonb_subscript_assign(ExprState *state,
+					   ExprEvalStep *op,
+					   ExprContext *econtext)
+{
+	SubscriptingRefState *sbsrefstate = op->d.sbsref.state;
+	JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace;
+	Jsonb		*jsonbSource;
+	JsonbValue	*replacevalue;
+
+	if (sbsrefstate->replacenull)
+	{
+		replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue));
+		replacevalue->type = jbvNull;
+	}
+	else
+		replacevalue =
+			JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue));
+
+	/*
+	 * In case if the input container is null, set up an empty jsonb and
+	 * proceed with the assignment.
+	 */
+	if (*op->resnull)
+	{
+		JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue));
+
+		/*
+		 * To avoid any surprising results, set up an empty jsonb array in case
+		 * of an array is expected (i.e. the first subscript is integer),
+		 * otherwise jsonb object.
+		 */
+		if (workspace->expectArray)
+		{
+			newSource->type = jbvArray;
+			newSource->val.array.nElems = 0;
+			newSource->val.array.rawScalar = false;
+		}
+		else
+		{
+			newSource->type = jbvObject;
+			newSource->val.object.nPairs = 0;
+		}
+
+		jsonbSource = JsonbValueToJsonb(newSource);
+		*op->resnull = false;
+	}
+	else
+		jsonbSource = DatumGetJsonbP(*op->resvalue);
+
+	*op->resvalue = jsonb_set_element(jsonbSource,
+									  workspace->index,
+									  sbsrefstate->numupper,
+									  replacevalue);
+	/* The result is never NULL, so no need to change *op->resnull */
+}
+
+/*
+ * Compute old jsonb element value for a SubscriptingRef assignment
+ * expression.  Will only be called if the new-value subexpression
+ * contains SubscriptingRef or FieldStore.  This is the same as the
+ * regular fetch case, except that we have to handle a null jsonb,
+ * and the value should be stored into the SubscriptingRefState's
+ * prevvalue/prevnull fields.
+ */
+static void
+jsonb_subscript_fetch_old(ExprState *state,
+						  ExprEvalStep *op,
+						  ExprContext *econtext)
+{
+	SubscriptingRefState *sbsrefstate = op->d.sbsref.state;
+
+	if (*op->resnull)
+	{
+		/* whole jsonb is null, so any element is too */
+		sbsrefstate->prevvalue = (Datum) 0;
+		sbsrefstate->prevnull = true;
+	}
+	else
+	{
+		Jsonb	*jsonbSource = DatumGetJsonbP(*op->resvalue);
+		sbsrefstate->prevvalue = jsonb_get_element(jsonbSource,
+									  			   sbsrefstate->upperindex,
+									  			   sbsrefstate->numupper,
+												   &sbsrefstate->prevnull,
+												   false);
+	}
+}
+
+/*
+ * Set up execution state for a jsonb subscript operation. Opposite to the
+ * arrays subscription, there is no limit for number of subscripts as jsonb
+ * type itself doesn't have nesting limits.
+ */
+static void
+jsonb_exec_setup(const SubscriptingRef *sbsref,
+				 SubscriptingRefState *sbsrefstate,
+				 SubscriptExecSteps *methods)
+{
+	JsonbSubWorkspace *workspace;
+	ListCell   *lc;
+	int			nupper = sbsref->refupperindexpr->length;
+	char	   *ptr;
+
+	/* Allocate type-specific workspace with space for per-subscript data */
+	workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) +
+					    nupper * (sizeof(Datum) + sizeof(Oid)));
+	workspace->expectArray = false;
+	ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace));
+	workspace->indexOid = (Oid *) ptr;
+	ptr += nupper * sizeof(Oid);
+	workspace->index = (Datum *) ptr;
+
+	sbsrefstate->workspace = workspace;
+
+	/* Collect subscript data types necessary at execution time */
+	foreach(lc, sbsref->refupperindexpr)
+	{
+		Node   *expr = lfirst(lc);
+		int 	i = foreach_current_index(lc);
+
+		workspace->indexOid[i] = exprType(expr);
+	}
+
+	/*
+	 * Pass back pointers to appropriate step execution functions.
+	 */
+	methods->sbs_check_subscripts = jsonb_subscript_check_subscripts;
+	methods->sbs_fetch = jsonb_subscript_fetch;
+	methods->sbs_assign = jsonb_subscript_assign;
+	methods->sbs_fetch_old = jsonb_subscript_fetch_old;
+}
+
+/*
+ * jsonb_subscript_handler
+ *		Subscripting handler for jsonb.
+ *
+ */
+Datum
+jsonb_subscript_handler(PG_FUNCTION_ARGS)
+{
+	static const SubscriptRoutines sbsroutines = {
+		.transform = jsonb_subscript_transform,
+		.exec_setup = jsonb_exec_setup,
+		.fetch_strict = true,		/* fetch returns NULL for NULL inputs */
+		.fetch_leakproof = true,	/* fetch returns NULL for bad subscript */
+		.store_leakproof = false	/* ... but assignment throws error */
+	};
+
+	PG_RETURN_POINTER(&sbsroutines);
+}
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 69100feab7..5a0ba6b220 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname,
 /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */
 static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
 								  JsonbParseState **state);
-static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems,
+extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems,
 						   bool *path_nulls, int path_len,
-						   JsonbParseState **st, int level, Jsonb *newval,
+						   JsonbParseState **st, int level, JsonbValue *newval,
 						   int op_type);
 static void setPathObject(JsonbIterator **it, Datum *path_elems,
 						  bool *path_nulls, int path_len, JsonbParseState **st,
 						  int level,
-						  Jsonb *newval, uint32 npairs, int op_type);
+						  JsonbValue *newval, uint32 npairs, int op_type);
 static void setPathArray(JsonbIterator **it, Datum *path_elems,
 						 bool *path_nulls, int path_len, JsonbParseState **st,
-						 int level, Jsonb *newval, uint32 nelems, int op_type);
-static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb);
+						 int level,
+						 JsonbValue *newval, uint32 nelems, int op_type);
 
 /* function supporting iterate_json_values */
 static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype);
@@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text)
 	ArrayType  *path = PG_GETARG_ARRAYTYPE_P(1);
 	Datum	   *pathtext;
 	bool	   *pathnulls;
+	bool		isnull;
 	int			npath;
-	int			i;
-	bool		have_object = false,
-				have_array = false;
-	JsonbValue *jbvp = NULL;
-	JsonbValue	jbvbuf;
-	JsonbContainer *container;
+	Datum		res;
 
 	/*
 	 * If the array contains any null elements, return NULL, on the grounds
@@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text)
 	deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT,
 					  &pathtext, &pathnulls, &npath);
 
-	/* Identify whether we have object, array, or scalar at top-level */
-	container = &jb->root;
+	res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text);
 
+	if (isnull)
+		PG_RETURN_NULL();
+	else
+		PG_RETURN_DATUM(res);
+}
+
+Datum
+jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text)
+{
+	JsonbContainer *container = &jb->root;
+	JsonbValue	   *jbvp = NULL;
+	int				i;
+	bool			have_object = false,
+					have_array = false;
+
+	*isnull = false;
+
+	/* Identify whether we have object, array, or scalar at top-level */
 	if (JB_ROOT_IS_OBJECT(jb))
 		have_object = true;
 	else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb))
@@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text)
 	{
 		if (as_text)
 		{
-			PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL,
+			return PointerGetDatum(cstring_to_text(JsonbToCString(NULL,
 															container,
 															VARSIZE(jb))));
 		}
@@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text)
 		if (have_object)
 		{
 			jbvp = getKeyJsonValueFromContainer(container,
-												VARDATA(pathtext[i]),
-												VARSIZE(pathtext[i]) - VARHDRSZ,
-												&jbvbuf);
+												VARDATA(path[i]),
+												VARSIZE(path[i]) - VARHDRSZ,
+												NULL);
 		}
 		else if (have_array)
 		{
 			long		lindex;
 			uint32		index;
-			char	   *indextext = TextDatumGetCString(pathtext[i]);
+			char	   *indextext = TextDatumGetCString(path[i]);
 			char	   *endptr;
 
 			errno = 0;
 			lindex = strtol(indextext, &endptr, 10);
 			if (endptr == indextext || *endptr != '\0' || errno != 0 ||
 				lindex > INT_MAX || lindex < INT_MIN)
-				PG_RETURN_NULL();
+			{
+				*isnull = true;
+				return PointerGetDatum(NULL);
+			}
 
 			if (lindex >= 0)
 			{
@@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text)
 				nelements = JsonContainerSize(container);
 
 				if (-lindex > nelements)
-					PG_RETURN_NULL();
+				{
+					*isnull = true;
+					return PointerGetDatum(NULL);
+				}
 				else
 					index = nelements + lindex;
 			}
@@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text)
 		else
 		{
 			/* scalar, extraction yields a null */
-			PG_RETURN_NULL();
+			*isnull = true;
+			return PointerGetDatum(NULL);
 		}
 
 		if (jbvp == NULL)
-			PG_RETURN_NULL();
+		{
+			*isnull = true;
+			return PointerGetDatum(NULL);
+		}
 		else if (i == npath - 1)
 			break;
 
@@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text)
 	if (as_text)
 	{
 		if (jbvp->type == jbvNull)
-			PG_RETURN_NULL();
+		{
+			*isnull = true;
+			return PointerGetDatum(NULL);
+		}
 
-		PG_RETURN_TEXT_P(JsonbValueAsText(jbvp));
+		return PointerGetDatum(JsonbValueAsText(jbvp));
 	}
 	else
 	{
@@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text)
 	}
 }
 
+Datum
+jsonb_set_element(Jsonb* jb, Datum *path, int path_len,
+				  JsonbValue *newval)
+{
+	JsonbValue		   *res;
+	JsonbParseState    *state = NULL;
+	JsonbIterator 	   *it;
+	bool			   *path_nulls = palloc0(path_len * sizeof(bool));
+
+	if (newval->type == jbvArray && newval->val.array.rawScalar)
+		*newval = newval->val.array.elems[0];
+
+	it = JsonbIteratorInit(&jb->root);
+
+	res = setPath(&it, path, path_nulls, path_len, &state, 0,
+				  newval, JB_PATH_CREATE);
+
+	pfree(path_nulls);
+
+	PG_RETURN_JSONB_P(JsonbValueToJsonb(res));
+}
+
 /*
  * Return the text representation of the given JsonbValue.
  */
@@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS)
 	PG_RETURN_POINTER(JsonbValueToJsonb(res));
 }
 
-/*
- * Add values from the jsonb to the parse state.
- *
- * If the parse state container is an object, the jsonb is pushed as
- * a value, not a key.
- *
- * This needs to be done using an iterator because pushJsonbValue doesn't
- * like getting jbvBinary values, so we can't just push jb as a whole.
- */
-static void
-addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb)
-{
-	JsonbIterator *it;
-	JsonbValue *o = &(*jbps)->contVal;
-	JsonbValue	v;
-	JsonbIteratorToken type;
-
-	it = JsonbIteratorInit(&jb->root);
-
-	Assert(o->type == jbvArray || o->type == jbvObject);
-
-	if (JB_ROOT_IS_SCALAR(jb))
-	{
-		(void) JsonbIteratorNext(&it, &v, false);	/* skip array header */
-		Assert(v.type == jbvArray);
-		(void) JsonbIteratorNext(&it, &v, false);	/* fetch scalar value */
-
-		switch (o->type)
-		{
-			case jbvArray:
-				(void) pushJsonbValue(jbps, WJB_ELEM, &v);
-				break;
-			case jbvObject:
-				(void) pushJsonbValue(jbps, WJB_VALUE, &v);
-				break;
-			default:
-				elog(ERROR, "unexpected parent of nested structure");
-		}
-	}
-	else
-	{
-		while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE)
-		{
-			if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM)
-				(void) pushJsonbValue(jbps, type, &v);
-			else
-				(void) pushJsonbValue(jbps, type, NULL);
-		}
-	}
-
-}
-
 /*
  * SQL function jsonb_pretty (jsonb)
  *
@@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS)
 {
 	Jsonb	   *in = PG_GETARG_JSONB_P(0);
 	ArrayType  *path = PG_GETARG_ARRAYTYPE_P(1);
-	Jsonb	   *newval = PG_GETARG_JSONB_P(2);
+	Jsonb	   *newjsonb = PG_GETARG_JSONB_P(2);
+	JsonbValue *newval = JsonbToJsonbValue(newjsonb);
 	bool		create = PG_GETARG_BOOL(3);
 	JsonbValue *res = NULL;
 	Datum	   *path_elems;
@@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS)
 {
 	Jsonb	   *in = PG_GETARG_JSONB_P(0);
 	ArrayType  *path = PG_GETARG_ARRAYTYPE_P(1);
-	Jsonb	   *newval = PG_GETARG_JSONB_P(2);
+	Jsonb	   *newjsonb = PG_GETARG_JSONB_P(2);
+	JsonbValue *newval = JsonbToJsonbValue(newjsonb);
 	bool		after = PG_GETARG_BOOL(3);
 	JsonbValue *res = NULL;
 	Datum	   *path_elems;
@@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2,
  * All path elements before the last must already exist
  * whatever bits in op_type are set, or nothing is done.
  */
-static JsonbValue *
+JsonbValue *
 setPath(JsonbIterator **it, Datum *path_elems,
 		bool *path_nulls, int path_len,
-		JsonbParseState **st, int level, Jsonb *newval, int op_type)
+		JsonbParseState **st, int level, JsonbValue *newval, int op_type)
 {
 	JsonbValue	v;
 	JsonbIteratorToken r;
@@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems,
 static void
 setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			  int path_len, JsonbParseState **st, int level,
-			  Jsonb *newval, uint32 npairs, int op_type)
+			  JsonbValue *newval, uint32 npairs, int op_type)
 {
-	JsonbValue	v;
 	int			i;
-	JsonbValue	k;
+	JsonbValue	k,
+				v;
 	bool		done = false;
 
 	if (level >= path_len || path_nulls[level])
@@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 		newkey.val.string.val = VARDATA_ANY(path_elems[level]);
 
 		(void) pushJsonbValue(st, WJB_KEY, &newkey);
-		addJsonbToParseState(st, newval);
+		(void) pushJsonbValue(st, WJB_VALUE, newval);
 	}
 
 	for (i = 0; i < npairs; i++)
@@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 				if (!(op_type & JB_PATH_DELETE))
 				{
 					(void) pushJsonbValue(st, WJB_KEY, &k);
-					addJsonbToParseState(st, newval);
+					(void) pushJsonbValue(st, WJB_VALUE, newval);
 				}
 				done = true;
 			}
@@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 				newkey.val.string.val = VARDATA_ANY(path_elems[level]);
 
 				(void) pushJsonbValue(st, WJB_KEY, &newkey);
-				addJsonbToParseState(st, newval);
+				(void) pushJsonbValue(st, WJB_VALUE, newval);
 			}
 
 			(void) pushJsonbValue(st, r, &k);
@@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 static void
 setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			 int path_len, JsonbParseState **st, int level,
-			 Jsonb *newval, uint32 nelems, int op_type)
+			 JsonbValue *newval, uint32 nelems, int op_type)
 {
 	JsonbValue	v;
 	int			idx,
@@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 		(op_type & JB_PATH_CREATE_OR_INSERT))
 	{
 		Assert(newval != NULL);
-		addJsonbToParseState(st, newval);
+		(void) pushJsonbValue(st, WJB_ELEM, newval);
 		done = true;
 	}
 
@@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 				r = JsonbIteratorNext(it, &v, true);	/* skip */
 
 				if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE))
-					addJsonbToParseState(st, newval);
+					(void) pushJsonbValue(st, WJB_ELEM, newval);
 
 				/*
 				 * We should keep current value only in case of
@@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 					(void) pushJsonbValue(st, r, &v);
 
 				if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE))
-					addJsonbToParseState(st, newval);
+					(void) pushJsonbValue(st, WJB_ELEM, newval);
 
 				done = true;
 			}
@@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls,
 			if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done &&
 				level == path_len - 1 && i == nelems - 1)
 			{
-				addJsonbToParseState(st, newval);
+				(void) pushJsonbValue(st, WJB_ELEM, newval);
 			}
 		}
 	}
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 139f4a08bd..feae8cc4b0 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -11239,6 +11239,10 @@
 { oid => '9256', descr => 'raw array subscripting support',
   proname => 'raw_array_subscript_handler', prorettype => 'internal',
   proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' },
+# type subscripting support
+{ oid => '6098', descr => 'jsonb subscripting logic',
+  proname => 'jsonb_subscript_handler', prorettype => 'internal',
+  proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' },
 
 # collation management functions
 { oid => '3445', descr => 'import collations from operating system',
diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat
index 62018f063a..4a530ca907 100644
--- a/src/include/catalog/pg_type.dat
+++ b/src/include/catalog/pg_type.dat
@@ -444,7 +444,8 @@
 { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON',
   typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U',
   typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv',
-  typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' },
+  typsend => 'jsonb_send', typalign => 'i', typstorage => 'x',
+  typsubscript => 'jsonb_subscript_handler' },
 { oid => '4072', array_type_oid => '4073', descr => 'JSON path',
   typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U',
   typinput => 'jsonpath_in', typoutput => 'jsonpath_out',
diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h
index 5860011693..64f1ccbf77 100644
--- a/src/include/utils/jsonb.h
+++ b/src/include/utils/jsonb.h
@@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate,
 extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container);
 extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val,
 											bool skipNested);
+extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb);
 extern Jsonb *JsonbValueToJsonb(JsonbValue *val);
 extern bool JsonbDeepContains(JsonbIterator **val,
 							  JsonbIterator **mContained);
@@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in,
 extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res);
 extern const char *JsonbTypeName(JsonbValue *jb);
 
-
+extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len,
+							   JsonbValue *newval);
+extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath,
+							   bool *isnull, bool as_text);
 #endif							/* __JSONB_H__ */
diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index 1e6c6ef200..bb3f25ec3f 100644
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_
  {"a": 1, "b": null}
 (1 row)
 
-\pset null
+\pset null ''
 -- jsonb_insert
 select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"');
          jsonb_insert          
@@ -4729,6 +4729,276 @@ HINT:  Try using the function jsonb_set to replace key value.
 select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true);
 ERROR:  cannot replace existing key
 HINT:  Try using the function jsonb_set to replace key value.
+-- jsonb subscript
+select ('123'::jsonb)['a'];
+ jsonb 
+-------
+ 
+(1 row)
+
+select ('123'::jsonb)[0];
+ jsonb 
+-------
+ 
+(1 row)
+
+select ('123'::jsonb)[NULL];
+ jsonb 
+-------
+ 
+(1 row)
+
+select ('{"a": 1}'::jsonb)['a'];
+ jsonb 
+-------
+ 1
+(1 row)
+
+select ('{"a": 1}'::jsonb)[0];
+ jsonb 
+-------
+ 
+(1 row)
+
+select ('{"a": 1}'::jsonb)['not_exist'];
+ jsonb 
+-------
+ 
+(1 row)
+
+select ('{"a": 1}'::jsonb)[NULL];
+ jsonb 
+-------
+ 
+(1 row)
+
+select ('[1, "2", null]'::jsonb)['a'];
+ jsonb 
+-------
+ 
+(1 row)
+
+select ('[1, "2", null]'::jsonb)[0];
+ jsonb 
+-------
+ 1
+(1 row)
+
+select ('[1, "2", null]'::jsonb)['1'];
+ jsonb 
+-------
+ "2"
+(1 row)
+
+select ('[1, "2", null]'::jsonb)[1.0];
+ERROR:  subscript type is not supported
+LINE 1: select ('[1, "2", null]'::jsonb)[1.0];
+                                         ^
+HINT:  Jsonb subscript must be coercet to either integer or text
+select ('[1, "2", null]'::jsonb)[2];
+ jsonb 
+-------
+ null
+(1 row)
+
+select ('[1, "2", null]'::jsonb)[3];
+ jsonb 
+-------
+ 
+(1 row)
+
+select ('[1, "2", null]'::jsonb)[-2];
+ jsonb 
+-------
+ "2"
+(1 row)
+
+select ('[1, "2", null]'::jsonb)[1]['a'];
+ jsonb 
+-------
+ 
+(1 row)
+
+select ('[1, "2", null]'::jsonb)[1][0];
+ jsonb 
+-------
+ 
+(1 row)
+
+select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b'];
+ jsonb 
+-------
+ "c"
+(1 row)
+
+select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'];
+   jsonb   
+-----------
+ [1, 2, 3]
+(1 row)
+
+select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1];
+ jsonb 
+-------
+ 2
+(1 row)
+
+select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a'];
+ jsonb 
+-------
+ 
+(1 row)
+
+select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1'];
+     jsonb     
+---------------
+ {"a2": "aaa"}
+(1 row)
+
+select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2'];
+ jsonb 
+-------
+ "aaa"
+(1 row)
+
+select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3'];
+ jsonb 
+-------
+ 
+(1 row)
+
+select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'];
+         jsonb         
+-----------------------
+ ["aaa", "bbb", "ccc"]
+(1 row)
+
+select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2];
+ jsonb 
+-------
+ "ccc"
+(1 row)
+
+-- slices are not supported
+select ('{"a": 1}'::jsonb)['a':'b'];
+ERROR:  jsonb subscript does not support slices
+LINE 1: select ('{"a": 1}'::jsonb)['a':'b'];
+                                       ^
+select ('[1, "2", null]'::jsonb)[1:2];
+ERROR:  jsonb subscript does not support slices
+LINE 1: select ('[1, "2", null]'::jsonb)[1:2];
+                                           ^
+select ('[1, "2", null]'::jsonb)[:2];
+ERROR:  jsonb subscript does not support slices
+LINE 1: select ('[1, "2", null]'::jsonb)[:2];
+                                          ^
+select ('[1, "2", null]'::jsonb)[1:];
+ERROR:  jsonb subscript does not support slices
+LINE 1: select ('[1, "2", null]'::jsonb)[1:];
+                                         ^
+select ('[1, "2", null]'::jsonb)[:];
+ERROR:  jsonb subscript does not support slices
+create TEMP TABLE test_jsonb_subscript (
+       id int,
+       test_json jsonb
+);
+insert into test_jsonb_subscript values
+(1, '{}'), -- empty jsonb
+(2, '{"key": "value"}'); -- jsonb with data
+-- update empty jsonb
+update test_jsonb_subscript set test_json['a'] = '1' where id = 1;
+select * from test_jsonb_subscript;
+ id |    test_json     
+----+------------------
+  2 | {"key": "value"}
+  1 | {"a": 1}
+(2 rows)
+
+-- update jsonb with some data
+update test_jsonb_subscript set test_json['a'] = '1' where id = 2;
+select * from test_jsonb_subscript;
+ id |        test_json         
+----+--------------------------
+  1 | {"a": 1}
+  2 | {"a": 1, "key": "value"}
+(2 rows)
+
+-- replace jsonb
+update test_jsonb_subscript set test_json['a'] = '"test"';
+select * from test_jsonb_subscript;
+ id |           test_json           
+----+-------------------------------
+  1 | {"a": "test"}
+  2 | {"a": "test", "key": "value"}
+(2 rows)
+
+-- replace by object
+update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb;
+select * from test_jsonb_subscript;
+ id |            test_json            
+----+---------------------------------
+  1 | {"a": {"b": 1}}
+  2 | {"a": {"b": 1}, "key": "value"}
+(2 rows)
+
+-- replace by array
+update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb;
+select * from test_jsonb_subscript;
+ id |            test_json             
+----+----------------------------------
+  1 | {"a": [1, 2, 3]}
+  2 | {"a": [1, 2, 3], "key": "value"}
+(2 rows)
+
+-- use jsonb subscription in where clause
+select * from test_jsonb_subscript where test_json['key'] = '"value"';
+ id |            test_json             
+----+----------------------------------
+  2 | {"a": [1, 2, 3], "key": "value"}
+(1 row)
+
+select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"';
+ id | test_json 
+----+-----------
+(0 rows)
+
+select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"';
+ id | test_json 
+----+-----------
+(0 rows)
+
+-- NULL
+update test_jsonb_subscript set test_json[NULL] = '1';
+ERROR:  jsonb subscript in assignment must not be null
+update test_jsonb_subscript set test_json['another_key'] = NULL;
+select * from test_jsonb_subscript;
+ id |                       test_json                       
+----+-------------------------------------------------------
+  1 | {"a": [1, 2, 3], "another_key": null}
+  2 | {"a": [1, 2, 3], "key": "value", "another_key": null}
+(2 rows)
+
+-- NULL as jsonb source
+insert into test_jsonb_subscript values (3, NULL);
+update test_jsonb_subscript set test_json['a'] = '1' where id = 3;
+select * from test_jsonb_subscript;
+ id |                       test_json                       
+----+-------------------------------------------------------
+  1 | {"a": [1, 2, 3], "another_key": null}
+  2 | {"a": [1, 2, 3], "key": "value", "another_key": null}
+  3 | {"a": 1}
+(3 rows)
+
+update test_jsonb_subscript set test_json = NULL where id = 3;
+update test_jsonb_subscript set test_json[0] = '1';
+select * from test_jsonb_subscript;
+ id |                           test_json                           
+----+---------------------------------------------------------------
+  1 | {"0": 1, "a": [1, 2, 3], "another_key": null}
+  2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null}
+  3 | [1]
+(3 rows)
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
                                 to_tsvector                                
diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql
index b6409767f6..20aa8fe0e2 100644
--- a/src/test/regress/sql/jsonb.sql
+++ b/src/test/regress/sql/jsonb.sql
@@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu
 select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key;
 select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null;
 
-\pset null
+\pset null ''
 
 -- jsonb_insert
 select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"');
@@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true);
 select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"');
 select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true);
 
+-- jsonb subscript
+select ('123'::jsonb)['a'];
+select ('123'::jsonb)[0];
+select ('123'::jsonb)[NULL];
+select ('{"a": 1}'::jsonb)['a'];
+select ('{"a": 1}'::jsonb)[0];
+select ('{"a": 1}'::jsonb)['not_exist'];
+select ('{"a": 1}'::jsonb)[NULL];
+select ('[1, "2", null]'::jsonb)['a'];
+select ('[1, "2", null]'::jsonb)[0];
+select ('[1, "2", null]'::jsonb)['1'];
+select ('[1, "2", null]'::jsonb)[1.0];
+select ('[1, "2", null]'::jsonb)[2];
+select ('[1, "2", null]'::jsonb)[3];
+select ('[1, "2", null]'::jsonb)[-2];
+select ('[1, "2", null]'::jsonb)[1]['a'];
+select ('[1, "2", null]'::jsonb)[1][0];
+select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b'];
+select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'];
+select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1];
+select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a'];
+select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1'];
+select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2'];
+select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3'];
+select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'];
+select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2];
+
+-- slices are not supported
+select ('{"a": 1}'::jsonb)['a':'b'];
+select ('[1, "2", null]'::jsonb)[1:2];
+select ('[1, "2", null]'::jsonb)[:2];
+select ('[1, "2", null]'::jsonb)[1:];
+select ('[1, "2", null]'::jsonb)[:];
+
+create TEMP TABLE test_jsonb_subscript (
+       id int,
+       test_json jsonb
+);
+
+insert into test_jsonb_subscript values
+(1, '{}'), -- empty jsonb
+(2, '{"key": "value"}'); -- jsonb with data
+
+-- update empty jsonb
+update test_jsonb_subscript set test_json['a'] = '1' where id = 1;
+select * from test_jsonb_subscript;
+
+-- update jsonb with some data
+update test_jsonb_subscript set test_json['a'] = '1' where id = 2;
+select * from test_jsonb_subscript;
+
+-- replace jsonb
+update test_jsonb_subscript set test_json['a'] = '"test"';
+select * from test_jsonb_subscript;
+
+-- replace by object
+update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb;
+select * from test_jsonb_subscript;
+
+-- replace by array
+update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb;
+select * from test_jsonb_subscript;
+
+-- use jsonb subscription in where clause
+select * from test_jsonb_subscript where test_json['key'] = '"value"';
+select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"';
+select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"';
+
+-- NULL
+update test_jsonb_subscript set test_json[NULL] = '1';
+update test_jsonb_subscript set test_json['another_key'] = NULL;
+select * from test_jsonb_subscript;
+
+-- NULL as jsonb source
+insert into test_jsonb_subscript values (3, NULL);
+update test_jsonb_subscript set test_json['a'] = '1' where id = 3;
+select * from test_jsonb_subscript;
+
+update test_jsonb_subscript set test_json = NULL where id = 3;
+update test_jsonb_subscript set test_json[0] = '1';
+select * from test_jsonb_subscript;
+
 -- jsonb to tsvector
 select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb);
 
-- 
2.21.0


--6snw7vcvuujiswgu
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v43-0002-Filling-gaps-in-jsonb.patch"



^ permalink  raw  reply  [nested|flat] 259+ messages in thread

* [PATCH v38 09/11] Add support for min/max aggregates for IVM
@ 2023-05-31 11:58  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 259+ messages in thread

From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw)

Supporting min and max is more complicated than count, sum, or avg.

For an example of min, when tuples are inserted, the current min value
in the view and the min value in the inseteted tuples are compared,
then the smaller one is used as the latest min value. On the other
hand, when tuples are deleted, if the current min value in the view
equals to the min in the deleted tuples, we need re-computation the
latest min value from base tables. Otherwise, the current value in
the view remains.
---
 src/backend/commands/createas.c |  45 +++
 src/backend/commands/matview.c  | 644 +++++++++++++++++++++++++++++++-
 2 files changed, 680 insertions(+), 9 deletions(-)

diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 35e124694ab..540d9e3d5c8 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid)
 		case F_AVG_FLOAT8:
 		case F_AVG_INTERVAL:
 
+		/* min */
+		case F_MIN_ANYARRAY:
+		case F_MIN_INT8:
+		case F_MIN_INT4:
+		case F_MIN_INT2:
+		case F_MIN_OID:
+		case F_MIN_FLOAT4:
+		case F_MIN_FLOAT8:
+		case F_MIN_DATE:
+		case F_MIN_TIME:
+		case F_MIN_TIMETZ:
+		case F_MIN_MONEY:
+		case F_MIN_TIMESTAMP:
+		case F_MIN_TIMESTAMPTZ:
+		case F_MIN_INTERVAL:
+		case F_MIN_TEXT:
+		case F_MIN_NUMERIC:
+		case F_MIN_BPCHAR:
+		case F_MIN_TID:
+		case F_MIN_ANYENUM:
+		case F_MIN_INET:
+		case F_MIN_PG_LSN:
+
+		/* max */
+		case F_MAX_ANYARRAY:
+		case F_MAX_INT8:
+		case F_MAX_INT4:
+		case F_MAX_INT2:
+		case F_MAX_OID:
+		case F_MAX_FLOAT4:
+		case F_MAX_FLOAT8:
+		case F_MAX_DATE:
+		case F_MAX_TIME:
+		case F_MAX_TIMETZ:
+		case F_MAX_MONEY:
+		case F_MAX_TIMESTAMP:
+		case F_MAX_TIMESTAMPTZ:
+		case F_MAX_INTERVAL:
+		case F_MAX_TEXT:
+		case F_MAX_NUMERIC:
+		case F_MAX_BPCHAR:
+		case F_MAX_TID:
+		case F_MAX_ANYENUM:
+		case F_MAX_INET:
+		case F_MAX_PG_LSN:
 			return true;
 
 		default:
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 710224aa994..3b3871c49e2 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -69,6 +69,34 @@ typedef struct
 
 #define MV_INIT_QUERYHASHSIZE	16
 
+/* MV query type codes */
+#define MV_PLAN_RECALC			1
+#define MV_PLAN_SET_VALUE		2
+
+/*
+ * MI_QueryKey
+ *
+ * The key identifying a prepared SPI plan in our query hashtable
+ */
+typedef struct MV_QueryKey
+{
+	Oid			matview_id;	/* OID of materialized view */
+	int32		query_type;	/* query type ID, see MV_PLAN_XXX above */
+} MV_QueryKey;
+
+/*
+ * MV_QueryHashEntry
+ *
+ * Hash entry for cached plans used to maintain materialized views.
+ */
+typedef struct MV_QueryHashEntry
+{
+	MV_QueryKey key;
+	SPIPlanPtr	plan;
+	SearchPathMatcher *search_path;        /* search_path used for parsing
+											 * and planning */
+} MV_QueryHashEntry;
+
 /*
  * MV_TriggerHashEntry
  *
@@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo
 } DroppedImmvInfo;
 
 static HTAB *mv_trigger_info = NULL;
+static HTAB *mv_query_cache = NULL;
 static HTAB *dropped_immv = NULL;
 
 static HTAB *LastIvmUpdateHash;
@@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old,
 static void append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 						  StringInfo buf_new, StringInfo aggs_list,
 						  const char *aggtype);
+static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min);
 static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2,
 					 const char* count_col, const char *castType);
 static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
@@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old,
 				List *keys);
 static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname);
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc);
 static void apply_new_delta(const char *matviewname, const char *deltaname_new,
 				StringInfo target_list);
 static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
 				List *keys, StringInfo target_list, StringInfo aggs_set,
 				const char* count_colname);
 static char *get_matching_condition_string(List *keys);
+static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys);
+static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list);
+static char *get_select_for_recalc_string(List *keys);
+static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel);
+static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes);
+static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes);
 static void generate_equal(StringInfo querybuf, Oid opttype,
 			   const char *leftop, const char *rightop);
 
 static void mv_InitHashTables(void);
+static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key);
+static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan);
+static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type);
 static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
 									SubTransactionId subxid);
 static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
@@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	ListCell	*lc;
 	int			i;
 	List	   *keys = NIL;
+	List	   *minmax_list = NIL;
+	List	   *is_min_list = NIL;
 
 
 	/*
@@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 				append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf,
 										  format_type_be(aggref->aggtype));
 
+			/* min/max */
+			else if (!strcmp(aggname, "min") || !strcmp(aggname, "max"))
+			{
+				bool	is_min = (!strcmp(aggname, "min"));
+
+				append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min);
+
+				/* make a resname list of min and max aggregates */
+				minmax_list = lappend(minmax_list, resname);
+				is_min_list = lappend_int(is_min_list, is_min);
+			}
 			else
 				elog(ERROR, "unsupported aggregate function: %s", aggname);
 		}
@@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
 	{
 		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		SPITupleTable  *tuptable_recalc = NULL;
+		uint64			num_recalc;
 		int				rc;
 
 		/* convert tuplestores to ENR, and register for SPI */
@@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 			/* apply old delta and get rows to be recalculated */
 			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
 									   keys, aggs_list_buf, aggs_set_old,
-									   count_colname);
+									   minmax_list, is_min_list,
+									   count_colname, &tuptable_recalc, &num_recalc);
 		else
 			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
 
+		/*
+		 * If we have min or max, we might have to recalculate aggregate values from base tables
+		 * on some tuples. TIDs and keys such tuples are returned as a result of the above query.
+		 */
+		if (minmax_list && tuptable_recalc)
+			recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel);
+
 	}
 	/* For tuple insertion */
 	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
@@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 	);
 }
 
+/*
+ * append_set_clause_for_minmax
+ *
+ * Append SET clause string for min or max aggregation to given buffers.
+ * Also, append resnames required for calculating the aggregate value.
+ * is_min is true if this is min, false if not.
+ */
+static void
+append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min)
+{
+	char *count_col = IVM_colname("count", resname);
+
+	/* For tuple deletion */
+	if (buf_old)
+	{
+		/*
+		 * If the new value doesn't became NULL then use the value remaining
+		 * in the view although this will be recomputated afterwords.
+		 */
+		appendStringInfo(buf_old,
+			", %s = CASE WHEN %s THEN NULL ELSE %s END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_SUB, "mv", "t", count_col),
+			quote_qualified_identifier("mv", resname)
+		);
+		/* count = mv.count - t.count */
+		appendStringInfo(buf_old,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL)
+		);
+	}
+	/* For tuple insertion */
+	if (buf_new)
+	{
+		/*
+		 * min = LEAST(mv.min, diff.min)
+		 * max = GREATEST(mv.max, diff.max)
+		 */
+		appendStringInfo(buf_new,
+			", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_ADD, "mv", "diff", count_col),
+
+			is_min ? "LEAST" : "GREATEST",
+			quote_qualified_identifier("mv", resname),
+			quote_qualified_identifier("diff", resname)
+		);
+		/* count = mv.count + diff.count */
+		appendStringInfo(buf_new,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL)
+		);
+	}
+
+	appendStringInfo(aggs_list, ", %s, %s",
+		quote_qualified_identifier("diff", resname),
+		quote_qualified_identifier("diff", IVM_colname("count", resname))
+	);
+}
+
 /*
  * get_operation_string
  *
@@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
  * list to identify a tuple in the view. If the view has aggregates, this
  * requires strings representing resnames of aggregates and SET clause for
  * updating aggregate values.
+ *
+ * If the view has min or max aggregate, this requires a list of resnames of
+ * min/max aggregates and a list of boolean which represents which entries in
+ * minmax_list is min. These are necessary to check if we need to recalculate
+ * min or max aggregate values. In this case, this query returns TID and keys
+ * of tuples which need to be recalculated.  This result and the number of rows
+ * are stored in tuptables and num_recalc repectedly.
+ *
  */
 static void
 apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname)
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc)
 {
 	StringInfoData	querybuf;
 	char   *match_cond;
+	char   *updt_returning = "";
+	char   *select_for_recalc = "SELECT";
 	bool	agg_without_groupby = (list_length(keys) == 0);
 
+	Assert(tuptable_recalc != NULL);
+	Assert(num_recalc != NULL);
+
 	/* build WHERE condition for searching tuples to be deleted */
 	match_cond = get_matching_condition_string(keys);
 
+	/*
+	 * We need a special RETURNING clause and SELECT statement for min/max to
+	 * check which tuple needs re-calculation from base tables.
+	 */
+	if (minmax_list)
+	{
+		updt_returning = get_returning_string(minmax_list, is_min_list, keys);
+		select_for_recalc = get_select_for_recalc_string(keys);
+	}
+
 	/* Search for matching tuples from the view and update or delete if found. */
 	initStringInfo(&querybuf);
 	appendStringInfo(&querybuf,
@@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
 											"%s"	/* SET clauses for aggregates */
 						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
-					")"
-					/* delete a tuple if this is to be deleted */
-					"DELETE FROM %s AS mv USING t "
-					"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt",
+						"%s"						/* RETURNING clause for recalc infomation */
+					"), dlt AS ("			/* delete a tuple if this is to be deleted */
+						"DELETE FROM %s AS mv USING t "
+						"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt"
+					") %s",							/* SELECT returning which tuples need to be recalculated */
 					count_colname,
 					count_colname, count_colname, (agg_without_groupby ? "false" : "true"),
 					(aggs_list != NULL ? aggs_list->data : ""),
@@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 					match_cond,
 					matviewname, count_colname, count_colname, count_colname,
 					(aggs_set != NULL ? aggs_set->data : ""),
-					matviewname);
+					updt_returning,
+					matviewname,
+					select_for_recalc);
 
-	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT)
 		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+
+
+	/* Return tuples to be recalculated. */
+	if (minmax_list)
+	{
+		*tuptable_recalc = SPI_tuptable;
+		*num_recalc = SPI_processed;
+	}
+	else
+	{
+		*tuptable_recalc = NULL;
+		*num_recalc = 0;
+	}
 }
 
 /*
@@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys)
 	return match_cond.data;
 }
 
+/*
+ * get_returning_string
+ *
+ * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count.
+ * This clause returns ctid and a boolean value that indicates if we need to
+ * recalculate min or max value, for each updated row.
+ */
+static char *
+get_returning_string(List *minmax_list, List *is_min_list, List *keys)
+{
+	StringInfoData returning;
+	char		*recalc_cond;
+	ListCell	*lc;
+
+	Assert(minmax_list != NIL && is_min_list != NIL);
+	recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list);
+
+	initStringInfo(&returning);
+
+	appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char *resname = NameStr(attr->attname);
+		appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname));
+	}
+
+	return returning.data;
+}
+
+/*
+ * get_minmax_recalc_condition_string
+ *
+ * Build a predicate string for checking if any min/max aggregate
+ * value needs to be recalculated.
+ */
+static char *
+get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list)
+{
+	StringInfoData recalc_cond;
+	ListCell	*lc1, *lc2;
+
+	initStringInfo(&recalc_cond);
+
+	Assert (list_length(minmax_list) == list_length(is_min_list));
+
+	forboth (lc1, minmax_list, lc2, is_min_list)
+	{
+		char   *resname = (char *) lfirst(lc1);
+		bool	is_min = (bool) lfirst_int(lc2);
+		char   *op_str = (is_min ? ">=" : "<=");
+
+		appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s",
+			quote_qualified_identifier("mv", resname),
+			op_str,
+			quote_qualified_identifier("t", resname)
+		);
+
+		if (lnext(minmax_list, lc1))
+			appendStringInfo(&recalc_cond, " OR ");
+	}
+
+	return recalc_cond.data;
+}
+
+/*
+ * get_select_for_recalc_string
+ *
+ * Build a query to return tid and keys of tuples which need
+ * recalculation. This is used as the result of the query
+ * built by apply_old_delta.
+ */
+static char *
+get_select_for_recalc_string(List *keys)
+{
+	StringInfoData qry;
+	ListCell	*lc;
+
+	initStringInfo(&qry);
+
+	appendStringInfo(&qry, "SELECT tid");
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		appendStringInfo(&qry, ", %s", NameStr(attr->attname));
+	}
+
+	appendStringInfo(&qry, " FROM updt WHERE recalc");
+
+	return qry.data;
+}
+
+/*
+ * recalc_and_set_values
+ *
+ * Recalculate tuples in a materialized from base tables and update these.
+ * The tuples which needs recalculation are specified by keys, and resnames
+ * of columns to be updated are specified by namelist. TIDs and key values
+ * are given by tuples in tuptable_recalc. Its first attribute must be TID
+ * and key values must be following this.
+ */
+static void
+recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel)
+{
+	TupleDesc   tupdesc_recalc = tuptable_recalc->tupdesc;
+	Oid		   *keyTypes = NULL, *types = NULL;
+	char	   *keyNulls = NULL, *nulls = NULL;
+	Datum	   *keyVals = NULL, *vals = NULL;
+	int			num_vals = list_length(namelist);
+	int			num_keys = list_length(keys);
+	uint64      i;
+	Oid			matviewOid;
+	char	   *matviewname;
+
+	matviewOid = RelationGetRelid(matviewRel);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/* If we have keys, initialize arrays for them. */
+	if (keys)
+	{
+		keyTypes = palloc(sizeof(Oid) * num_keys);
+		keyNulls = palloc(sizeof(char) * num_keys);
+		keyVals = palloc(sizeof(Datum) * num_keys);
+		/* a tuple contains keys to be recalculated and ctid to be updated*/
+		Assert(tupdesc_recalc->natts == num_keys + 1);
+
+		/* Types of key attributes  */
+		for (i = 0; i < num_keys; i++)
+			keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid;
+	}
+
+	/* allocate memory for all attribute names and tid */
+	types = palloc(sizeof(Oid) * (num_vals + 1));
+	nulls = palloc(sizeof(char) * (num_vals + 1));
+	vals = palloc(sizeof(Datum) * (num_vals + 1));
+
+	/* For each tuple which needs recalculation */
+	for (i = 0; i < num_tuples; i++)
+	{
+		int j;
+		bool isnull;
+		SPIPlanPtr plan;
+		SPITupleTable *tuptable_newvals;
+		TupleDesc   tupdesc_newvals;
+
+		/* Set group key values as parameters if needed. */
+		if (keys)
+		{
+			for (j = 0; j < num_keys; j++)
+			{
+				keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull);
+				if (isnull)
+					keyNulls[j] = 'n';
+				else
+					keyNulls[j] = ' ';
+			}
+		}
+
+		/*
+		 * Get recalculated values from base tables. The result must be
+		 * only one tuple thich contains the new values for specified keys.
+		 */
+		plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes);
+		if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT)
+			elog(ERROR, "SPI_execute_plan");
+		if (SPI_processed != 1)
+			elog(ERROR, "SPI_execute_plan returned zero or more than one rows");
+
+		tuptable_newvals = SPI_tuptable;
+		tupdesc_newvals = tuptable_newvals->tupdesc;
+
+		Assert(tupdesc_newvals->natts == num_vals);
+
+		/* Set the new values as parameters */
+		for (j = 0; j < tupdesc_newvals->natts; j++)
+		{
+			if (i == 0)
+				types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid;
+
+			vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull);
+			if (isnull)
+				nulls[j] = 'n';
+			else
+				nulls[j] = ' ';
+		}
+		/* Set TID of the view tuple to be updated as a parameter */
+		types[j] = TIDOID;
+		vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull);
+		nulls[j] = ' ';
+
+		/* Update the view tuple to the new values */
+		plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types);
+		if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE)
+			elog(ERROR, "SPI_execute_plan");
+	}
+}
+
+
+/*
+ * get_plan_for_recalc
+ *
+ * Create or fetch a plan for recalculating value in the view's target list
+ * from base tables using the definition query of materialized view specified
+ * by matviewOid. namelist is a list of resnames of values to be recalculated.
+ *
+ * keys is a list of keys to identify tuples to be recalculated if this is not
+ * empty. KeyTypes is an array of types of keys.
+ */
+static SPIPlanPtr
+get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes)
+{
+	MV_QueryKey hash_key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the recalculation */
+	mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC);
+	if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL)
+	{
+		ListCell	   *lc;
+		StringInfoData	str;
+		char   *viewdef;
+
+		/* get view definition of matview */
+		viewdef = text_to_cstring((text *) DatumGetPointer(
+					DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid))));
+		/* get rid of trailing semi-colon */
+		viewdef[strlen(viewdef)-1] = '\0';
+
+		/*
+		 * Build a query string for recalculating values. This is like
+		 *
+		 *  SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv
+		 *   WHERE (key1, key2, ...) = ($1, $2, ...);
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "SELECT ");
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, " FROM (%s) mv", viewdef);
+
+		if (keys)
+		{
+			int		i = 1;
+			char	paramname[16];
+
+			appendStringInfo(&str, " WHERE (");
+			foreach (lc, keys)
+			{
+				Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+				char   *resname = NameStr(attr->attname);
+				Oid		typid = attr->atttypid;
+
+				sprintf(paramname, "$%d", i);
+				appendStringInfo(&str, "(");
+				generate_equal(&str, typid, resname, paramname);
+				appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))",
+								 resname, paramname);
+
+				if (lnext(keys, lc))
+					appendStringInfoString(&str, " AND ");
+				i++;
+			}
+			appendStringInfo(&str, ")");
+		}
+		else
+			keyTypes = NULL;
+
+		plan = SPI_prepare(str.data, list_length(keys), keyTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&hash_key, plan);
+	}
+
+	return plan;
+}
+
+/*
+ * get_plan_for_set_values
+ *
+ * Create or fetch a plan for applying new values calculated by
+ * get_plan_for_recalc to a materialized view specified by matviewOid.
+ * matviewname is the name of the view.  namelist is a list of resnames
+ * of attributes to be updated, and valTypes is an array of types of the
+ * values.
+ */
+static SPIPlanPtr
+get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes)
+{
+	MV_QueryKey	key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the real check */
+	mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE);
+	if ((plan = mv_FetchPreparedPlan(&key)) == NULL)
+	{
+		ListCell	  *lc;
+		StringInfoData str;
+		int		i;
+
+		/*
+		 * Build a query string for applying min/max values. This is like
+		 *
+		 *  UPDATE matviewname AS mv
+		 *   SET (x1, x2, x3, x4) = ($1, $2, $3, $4)
+		 *   WHERE ctid = $5;
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname);
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, ") = ROW(");
+
+		for (i = 1; i <= list_length(namelist); i++)
+			appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i);
+
+		appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i);
+
+		plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&key, plan);
+	}
+
+	return plan;
+}
+
 /*
  * generate_equals
  *
@@ -3025,6 +3541,13 @@ mv_InitHashTables(void)
 {
 	HASHCTL		ctl;
 
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(MV_QueryKey);
+	ctl.entrysize = sizeof(MV_QueryHashEntry);
+	mv_query_cache = hash_create("MV query cache",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
 	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(MV_TriggerHashEntry);
@@ -3039,6 +3562,109 @@ mv_InitHashTables(void)
 							   &ctl, HASH_ELEM | HASH_BLOBS);
 }
 
+/*
+ * mv_FetchPreparedPlan
+ */
+static SPIPlanPtr
+mv_FetchPreparedPlan(MV_QueryKey *key)
+{
+	MV_QueryHashEntry *entry;
+	SPIPlanPtr	plan;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Lookup for the key
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_FIND, NULL);
+	if (entry == NULL)
+		return NULL;
+
+	/*
+	 * Check whether the plan is still valid.  If it isn't, we don't want to
+	 * simply rely on plancache.c to regenerate it; rather we should start
+	 * from scratch and rebuild the query text too.  This is to cover cases
+	 * such as table/column renames.  We depend on the plancache machinery to
+	 * detect possible invalidations, though.
+	 *
+	 * CAUTION: this check is only trustworthy if the caller has already
+	 * locked both materialized views and base tables.
+	 *
+	 * Also, check whether the search_path is still the same as when we made it.
+	 * If it isn't, we need to rebuild the query text because the result of
+	 * pg_ivm_get_viewdef() will change.
+	 */
+	plan = entry->plan;
+	if (plan && SPI_plan_is_valid(plan) &&
+		SearchPathMatchesCurrentEnvironment(entry->search_path))
+		return plan;
+
+	/*
+	 * Otherwise we might as well flush the cached plan now, to free a little
+	 * memory space before we make a new one.
+	 */
+	if (plan)
+		SPI_freeplan(plan);
+	if (entry->search_path)
+		pfree(entry->search_path);
+
+	entry->plan = NULL;
+	entry->search_path = NULL;
+
+	return NULL;
+}
+
+/*
+ * mv_HashPreparedPlan
+ *
+ * Add another plan to our private SPI query plan hashtable.
+ */
+static void
+mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan)
+{
+	MV_QueryHashEntry *entry;
+	bool		found;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Add the new plan.  We might be overwriting an entry previously found
+	 * invalid by mv_FetchPreparedPlan.
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_ENTER, &found);
+	Assert(!found || entry->plan == NULL);
+	entry->plan = plan;
+	entry->search_path = GetSearchPathMatcher(TopMemoryContext);
+}
+
+/*
+ * mv_BuildQueryKey
+ *
+ * Construct a hashtable key for a prepared SPI plan for IVM.
+ */
+static void
+mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type)
+{
+	/*
+	 * We assume struct MV_QueryKey contains no padding bytes, else we'd need
+	 * to use memset to clear them.
+	 */
+	key->matview_id = matview_id;
+	key->query_type = query_type;
+}
+
 /*
  * AtAbort_IVM
  *
-- 
2.43.0


--Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ
Content-Type: text/x-diff;
 name="v38-0008-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v38-0008-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 259+ messages in thread

* [PATCH v37 09/11] Add support for min/max aggregates for IVM
@ 2023-05-31 11:58  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 259+ messages in thread

From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw)

Supporting min and max is more complicated than count, sum, or avg.

For an example of min, when tuples are inserted, the current min value
in the view and the min value in the inseteted tuples are compared,
then the smaller one is used as the latest min value. On the other
hand, when tuples are deleted, if the current min value in the view
equals to the min in the deleted tuples, we need re-computation the
latest min value from base tables. Otherwise, the current value in
the view remains.
---
 src/backend/commands/createas.c |  45 +++
 src/backend/commands/matview.c  | 644 +++++++++++++++++++++++++++++++-
 2 files changed, 680 insertions(+), 9 deletions(-)

diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 45a30309951..ed67f399b7c 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid)
 		case F_AVG_FLOAT8:
 		case F_AVG_INTERVAL:
 
+		/* min */
+		case F_MIN_ANYARRAY:
+		case F_MIN_INT8:
+		case F_MIN_INT4:
+		case F_MIN_INT2:
+		case F_MIN_OID:
+		case F_MIN_FLOAT4:
+		case F_MIN_FLOAT8:
+		case F_MIN_DATE:
+		case F_MIN_TIME:
+		case F_MIN_TIMETZ:
+		case F_MIN_MONEY:
+		case F_MIN_TIMESTAMP:
+		case F_MIN_TIMESTAMPTZ:
+		case F_MIN_INTERVAL:
+		case F_MIN_TEXT:
+		case F_MIN_NUMERIC:
+		case F_MIN_BPCHAR:
+		case F_MIN_TID:
+		case F_MIN_ANYENUM:
+		case F_MIN_INET:
+		case F_MIN_PG_LSN:
+
+		/* max */
+		case F_MAX_ANYARRAY:
+		case F_MAX_INT8:
+		case F_MAX_INT4:
+		case F_MAX_INT2:
+		case F_MAX_OID:
+		case F_MAX_FLOAT4:
+		case F_MAX_FLOAT8:
+		case F_MAX_DATE:
+		case F_MAX_TIME:
+		case F_MAX_TIMETZ:
+		case F_MAX_MONEY:
+		case F_MAX_TIMESTAMP:
+		case F_MAX_TIMESTAMPTZ:
+		case F_MAX_INTERVAL:
+		case F_MAX_TEXT:
+		case F_MAX_NUMERIC:
+		case F_MAX_BPCHAR:
+		case F_MAX_TID:
+		case F_MAX_ANYENUM:
+		case F_MAX_INET:
+		case F_MAX_PG_LSN:
 			return true;
 
 		default:
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 710224aa994..3b3871c49e2 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -69,6 +69,34 @@ typedef struct
 
 #define MV_INIT_QUERYHASHSIZE	16
 
+/* MV query type codes */
+#define MV_PLAN_RECALC			1
+#define MV_PLAN_SET_VALUE		2
+
+/*
+ * MI_QueryKey
+ *
+ * The key identifying a prepared SPI plan in our query hashtable
+ */
+typedef struct MV_QueryKey
+{
+	Oid			matview_id;	/* OID of materialized view */
+	int32		query_type;	/* query type ID, see MV_PLAN_XXX above */
+} MV_QueryKey;
+
+/*
+ * MV_QueryHashEntry
+ *
+ * Hash entry for cached plans used to maintain materialized views.
+ */
+typedef struct MV_QueryHashEntry
+{
+	MV_QueryKey key;
+	SPIPlanPtr	plan;
+	SearchPathMatcher *search_path;        /* search_path used for parsing
+											 * and planning */
+} MV_QueryHashEntry;
+
 /*
  * MV_TriggerHashEntry
  *
@@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo
 } DroppedImmvInfo;
 
 static HTAB *mv_trigger_info = NULL;
+static HTAB *mv_query_cache = NULL;
 static HTAB *dropped_immv = NULL;
 
 static HTAB *LastIvmUpdateHash;
@@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old,
 static void append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 						  StringInfo buf_new, StringInfo aggs_list,
 						  const char *aggtype);
+static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min);
 static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2,
 					 const char* count_col, const char *castType);
 static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
@@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old,
 				List *keys);
 static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname);
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc);
 static void apply_new_delta(const char *matviewname, const char *deltaname_new,
 				StringInfo target_list);
 static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
 				List *keys, StringInfo target_list, StringInfo aggs_set,
 				const char* count_colname);
 static char *get_matching_condition_string(List *keys);
+static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys);
+static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list);
+static char *get_select_for_recalc_string(List *keys);
+static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel);
+static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes);
+static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes);
 static void generate_equal(StringInfo querybuf, Oid opttype,
 			   const char *leftop, const char *rightop);
 
 static void mv_InitHashTables(void);
+static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key);
+static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan);
+static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type);
 static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
 									SubTransactionId subxid);
 static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
@@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	ListCell	*lc;
 	int			i;
 	List	   *keys = NIL;
+	List	   *minmax_list = NIL;
+	List	   *is_min_list = NIL;
 
 
 	/*
@@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 				append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf,
 										  format_type_be(aggref->aggtype));
 
+			/* min/max */
+			else if (!strcmp(aggname, "min") || !strcmp(aggname, "max"))
+			{
+				bool	is_min = (!strcmp(aggname, "min"));
+
+				append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min);
+
+				/* make a resname list of min and max aggregates */
+				minmax_list = lappend(minmax_list, resname);
+				is_min_list = lappend_int(is_min_list, is_min);
+			}
 			else
 				elog(ERROR, "unsupported aggregate function: %s", aggname);
 		}
@@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
 	{
 		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		SPITupleTable  *tuptable_recalc = NULL;
+		uint64			num_recalc;
 		int				rc;
 
 		/* convert tuplestores to ENR, and register for SPI */
@@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 			/* apply old delta and get rows to be recalculated */
 			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
 									   keys, aggs_list_buf, aggs_set_old,
-									   count_colname);
+									   minmax_list, is_min_list,
+									   count_colname, &tuptable_recalc, &num_recalc);
 		else
 			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
 
+		/*
+		 * If we have min or max, we might have to recalculate aggregate values from base tables
+		 * on some tuples. TIDs and keys such tuples are returned as a result of the above query.
+		 */
+		if (minmax_list && tuptable_recalc)
+			recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel);
+
 	}
 	/* For tuple insertion */
 	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
@@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 	);
 }
 
+/*
+ * append_set_clause_for_minmax
+ *
+ * Append SET clause string for min or max aggregation to given buffers.
+ * Also, append resnames required for calculating the aggregate value.
+ * is_min is true if this is min, false if not.
+ */
+static void
+append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min)
+{
+	char *count_col = IVM_colname("count", resname);
+
+	/* For tuple deletion */
+	if (buf_old)
+	{
+		/*
+		 * If the new value doesn't became NULL then use the value remaining
+		 * in the view although this will be recomputated afterwords.
+		 */
+		appendStringInfo(buf_old,
+			", %s = CASE WHEN %s THEN NULL ELSE %s END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_SUB, "mv", "t", count_col),
+			quote_qualified_identifier("mv", resname)
+		);
+		/* count = mv.count - t.count */
+		appendStringInfo(buf_old,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL)
+		);
+	}
+	/* For tuple insertion */
+	if (buf_new)
+	{
+		/*
+		 * min = LEAST(mv.min, diff.min)
+		 * max = GREATEST(mv.max, diff.max)
+		 */
+		appendStringInfo(buf_new,
+			", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_ADD, "mv", "diff", count_col),
+
+			is_min ? "LEAST" : "GREATEST",
+			quote_qualified_identifier("mv", resname),
+			quote_qualified_identifier("diff", resname)
+		);
+		/* count = mv.count + diff.count */
+		appendStringInfo(buf_new,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL)
+		);
+	}
+
+	appendStringInfo(aggs_list, ", %s, %s",
+		quote_qualified_identifier("diff", resname),
+		quote_qualified_identifier("diff", IVM_colname("count", resname))
+	);
+}
+
 /*
  * get_operation_string
  *
@@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
  * list to identify a tuple in the view. If the view has aggregates, this
  * requires strings representing resnames of aggregates and SET clause for
  * updating aggregate values.
+ *
+ * If the view has min or max aggregate, this requires a list of resnames of
+ * min/max aggregates and a list of boolean which represents which entries in
+ * minmax_list is min. These are necessary to check if we need to recalculate
+ * min or max aggregate values. In this case, this query returns TID and keys
+ * of tuples which need to be recalculated.  This result and the number of rows
+ * are stored in tuptables and num_recalc repectedly.
+ *
  */
 static void
 apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname)
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc)
 {
 	StringInfoData	querybuf;
 	char   *match_cond;
+	char   *updt_returning = "";
+	char   *select_for_recalc = "SELECT";
 	bool	agg_without_groupby = (list_length(keys) == 0);
 
+	Assert(tuptable_recalc != NULL);
+	Assert(num_recalc != NULL);
+
 	/* build WHERE condition for searching tuples to be deleted */
 	match_cond = get_matching_condition_string(keys);
 
+	/*
+	 * We need a special RETURNING clause and SELECT statement for min/max to
+	 * check which tuple needs re-calculation from base tables.
+	 */
+	if (minmax_list)
+	{
+		updt_returning = get_returning_string(minmax_list, is_min_list, keys);
+		select_for_recalc = get_select_for_recalc_string(keys);
+	}
+
 	/* Search for matching tuples from the view and update or delete if found. */
 	initStringInfo(&querybuf);
 	appendStringInfo(&querybuf,
@@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
 											"%s"	/* SET clauses for aggregates */
 						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
-					")"
-					/* delete a tuple if this is to be deleted */
-					"DELETE FROM %s AS mv USING t "
-					"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt",
+						"%s"						/* RETURNING clause for recalc infomation */
+					"), dlt AS ("			/* delete a tuple if this is to be deleted */
+						"DELETE FROM %s AS mv USING t "
+						"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt"
+					") %s",							/* SELECT returning which tuples need to be recalculated */
 					count_colname,
 					count_colname, count_colname, (agg_without_groupby ? "false" : "true"),
 					(aggs_list != NULL ? aggs_list->data : ""),
@@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 					match_cond,
 					matviewname, count_colname, count_colname, count_colname,
 					(aggs_set != NULL ? aggs_set->data : ""),
-					matviewname);
+					updt_returning,
+					matviewname,
+					select_for_recalc);
 
-	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT)
 		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+
+
+	/* Return tuples to be recalculated. */
+	if (minmax_list)
+	{
+		*tuptable_recalc = SPI_tuptable;
+		*num_recalc = SPI_processed;
+	}
+	else
+	{
+		*tuptable_recalc = NULL;
+		*num_recalc = 0;
+	}
 }
 
 /*
@@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys)
 	return match_cond.data;
 }
 
+/*
+ * get_returning_string
+ *
+ * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count.
+ * This clause returns ctid and a boolean value that indicates if we need to
+ * recalculate min or max value, for each updated row.
+ */
+static char *
+get_returning_string(List *minmax_list, List *is_min_list, List *keys)
+{
+	StringInfoData returning;
+	char		*recalc_cond;
+	ListCell	*lc;
+
+	Assert(minmax_list != NIL && is_min_list != NIL);
+	recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list);
+
+	initStringInfo(&returning);
+
+	appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char *resname = NameStr(attr->attname);
+		appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname));
+	}
+
+	return returning.data;
+}
+
+/*
+ * get_minmax_recalc_condition_string
+ *
+ * Build a predicate string for checking if any min/max aggregate
+ * value needs to be recalculated.
+ */
+static char *
+get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list)
+{
+	StringInfoData recalc_cond;
+	ListCell	*lc1, *lc2;
+
+	initStringInfo(&recalc_cond);
+
+	Assert (list_length(minmax_list) == list_length(is_min_list));
+
+	forboth (lc1, minmax_list, lc2, is_min_list)
+	{
+		char   *resname = (char *) lfirst(lc1);
+		bool	is_min = (bool) lfirst_int(lc2);
+		char   *op_str = (is_min ? ">=" : "<=");
+
+		appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s",
+			quote_qualified_identifier("mv", resname),
+			op_str,
+			quote_qualified_identifier("t", resname)
+		);
+
+		if (lnext(minmax_list, lc1))
+			appendStringInfo(&recalc_cond, " OR ");
+	}
+
+	return recalc_cond.data;
+}
+
+/*
+ * get_select_for_recalc_string
+ *
+ * Build a query to return tid and keys of tuples which need
+ * recalculation. This is used as the result of the query
+ * built by apply_old_delta.
+ */
+static char *
+get_select_for_recalc_string(List *keys)
+{
+	StringInfoData qry;
+	ListCell	*lc;
+
+	initStringInfo(&qry);
+
+	appendStringInfo(&qry, "SELECT tid");
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		appendStringInfo(&qry, ", %s", NameStr(attr->attname));
+	}
+
+	appendStringInfo(&qry, " FROM updt WHERE recalc");
+
+	return qry.data;
+}
+
+/*
+ * recalc_and_set_values
+ *
+ * Recalculate tuples in a materialized from base tables and update these.
+ * The tuples which needs recalculation are specified by keys, and resnames
+ * of columns to be updated are specified by namelist. TIDs and key values
+ * are given by tuples in tuptable_recalc. Its first attribute must be TID
+ * and key values must be following this.
+ */
+static void
+recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel)
+{
+	TupleDesc   tupdesc_recalc = tuptable_recalc->tupdesc;
+	Oid		   *keyTypes = NULL, *types = NULL;
+	char	   *keyNulls = NULL, *nulls = NULL;
+	Datum	   *keyVals = NULL, *vals = NULL;
+	int			num_vals = list_length(namelist);
+	int			num_keys = list_length(keys);
+	uint64      i;
+	Oid			matviewOid;
+	char	   *matviewname;
+
+	matviewOid = RelationGetRelid(matviewRel);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/* If we have keys, initialize arrays for them. */
+	if (keys)
+	{
+		keyTypes = palloc(sizeof(Oid) * num_keys);
+		keyNulls = palloc(sizeof(char) * num_keys);
+		keyVals = palloc(sizeof(Datum) * num_keys);
+		/* a tuple contains keys to be recalculated and ctid to be updated*/
+		Assert(tupdesc_recalc->natts == num_keys + 1);
+
+		/* Types of key attributes  */
+		for (i = 0; i < num_keys; i++)
+			keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid;
+	}
+
+	/* allocate memory for all attribute names and tid */
+	types = palloc(sizeof(Oid) * (num_vals + 1));
+	nulls = palloc(sizeof(char) * (num_vals + 1));
+	vals = palloc(sizeof(Datum) * (num_vals + 1));
+
+	/* For each tuple which needs recalculation */
+	for (i = 0; i < num_tuples; i++)
+	{
+		int j;
+		bool isnull;
+		SPIPlanPtr plan;
+		SPITupleTable *tuptable_newvals;
+		TupleDesc   tupdesc_newvals;
+
+		/* Set group key values as parameters if needed. */
+		if (keys)
+		{
+			for (j = 0; j < num_keys; j++)
+			{
+				keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull);
+				if (isnull)
+					keyNulls[j] = 'n';
+				else
+					keyNulls[j] = ' ';
+			}
+		}
+
+		/*
+		 * Get recalculated values from base tables. The result must be
+		 * only one tuple thich contains the new values for specified keys.
+		 */
+		plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes);
+		if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT)
+			elog(ERROR, "SPI_execute_plan");
+		if (SPI_processed != 1)
+			elog(ERROR, "SPI_execute_plan returned zero or more than one rows");
+
+		tuptable_newvals = SPI_tuptable;
+		tupdesc_newvals = tuptable_newvals->tupdesc;
+
+		Assert(tupdesc_newvals->natts == num_vals);
+
+		/* Set the new values as parameters */
+		for (j = 0; j < tupdesc_newvals->natts; j++)
+		{
+			if (i == 0)
+				types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid;
+
+			vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull);
+			if (isnull)
+				nulls[j] = 'n';
+			else
+				nulls[j] = ' ';
+		}
+		/* Set TID of the view tuple to be updated as a parameter */
+		types[j] = TIDOID;
+		vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull);
+		nulls[j] = ' ';
+
+		/* Update the view tuple to the new values */
+		plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types);
+		if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE)
+			elog(ERROR, "SPI_execute_plan");
+	}
+}
+
+
+/*
+ * get_plan_for_recalc
+ *
+ * Create or fetch a plan for recalculating value in the view's target list
+ * from base tables using the definition query of materialized view specified
+ * by matviewOid. namelist is a list of resnames of values to be recalculated.
+ *
+ * keys is a list of keys to identify tuples to be recalculated if this is not
+ * empty. KeyTypes is an array of types of keys.
+ */
+static SPIPlanPtr
+get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes)
+{
+	MV_QueryKey hash_key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the recalculation */
+	mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC);
+	if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL)
+	{
+		ListCell	   *lc;
+		StringInfoData	str;
+		char   *viewdef;
+
+		/* get view definition of matview */
+		viewdef = text_to_cstring((text *) DatumGetPointer(
+					DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid))));
+		/* get rid of trailing semi-colon */
+		viewdef[strlen(viewdef)-1] = '\0';
+
+		/*
+		 * Build a query string for recalculating values. This is like
+		 *
+		 *  SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv
+		 *   WHERE (key1, key2, ...) = ($1, $2, ...);
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "SELECT ");
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, " FROM (%s) mv", viewdef);
+
+		if (keys)
+		{
+			int		i = 1;
+			char	paramname[16];
+
+			appendStringInfo(&str, " WHERE (");
+			foreach (lc, keys)
+			{
+				Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+				char   *resname = NameStr(attr->attname);
+				Oid		typid = attr->atttypid;
+
+				sprintf(paramname, "$%d", i);
+				appendStringInfo(&str, "(");
+				generate_equal(&str, typid, resname, paramname);
+				appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))",
+								 resname, paramname);
+
+				if (lnext(keys, lc))
+					appendStringInfoString(&str, " AND ");
+				i++;
+			}
+			appendStringInfo(&str, ")");
+		}
+		else
+			keyTypes = NULL;
+
+		plan = SPI_prepare(str.data, list_length(keys), keyTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&hash_key, plan);
+	}
+
+	return plan;
+}
+
+/*
+ * get_plan_for_set_values
+ *
+ * Create or fetch a plan for applying new values calculated by
+ * get_plan_for_recalc to a materialized view specified by matviewOid.
+ * matviewname is the name of the view.  namelist is a list of resnames
+ * of attributes to be updated, and valTypes is an array of types of the
+ * values.
+ */
+static SPIPlanPtr
+get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes)
+{
+	MV_QueryKey	key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the real check */
+	mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE);
+	if ((plan = mv_FetchPreparedPlan(&key)) == NULL)
+	{
+		ListCell	  *lc;
+		StringInfoData str;
+		int		i;
+
+		/*
+		 * Build a query string for applying min/max values. This is like
+		 *
+		 *  UPDATE matviewname AS mv
+		 *   SET (x1, x2, x3, x4) = ($1, $2, $3, $4)
+		 *   WHERE ctid = $5;
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname);
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, ") = ROW(");
+
+		for (i = 1; i <= list_length(namelist); i++)
+			appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i);
+
+		appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i);
+
+		plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&key, plan);
+	}
+
+	return plan;
+}
+
 /*
  * generate_equals
  *
@@ -3025,6 +3541,13 @@ mv_InitHashTables(void)
 {
 	HASHCTL		ctl;
 
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(MV_QueryKey);
+	ctl.entrysize = sizeof(MV_QueryHashEntry);
+	mv_query_cache = hash_create("MV query cache",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
 	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(MV_TriggerHashEntry);
@@ -3039,6 +3562,109 @@ mv_InitHashTables(void)
 							   &ctl, HASH_ELEM | HASH_BLOBS);
 }
 
+/*
+ * mv_FetchPreparedPlan
+ */
+static SPIPlanPtr
+mv_FetchPreparedPlan(MV_QueryKey *key)
+{
+	MV_QueryHashEntry *entry;
+	SPIPlanPtr	plan;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Lookup for the key
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_FIND, NULL);
+	if (entry == NULL)
+		return NULL;
+
+	/*
+	 * Check whether the plan is still valid.  If it isn't, we don't want to
+	 * simply rely on plancache.c to regenerate it; rather we should start
+	 * from scratch and rebuild the query text too.  This is to cover cases
+	 * such as table/column renames.  We depend on the plancache machinery to
+	 * detect possible invalidations, though.
+	 *
+	 * CAUTION: this check is only trustworthy if the caller has already
+	 * locked both materialized views and base tables.
+	 *
+	 * Also, check whether the search_path is still the same as when we made it.
+	 * If it isn't, we need to rebuild the query text because the result of
+	 * pg_ivm_get_viewdef() will change.
+	 */
+	plan = entry->plan;
+	if (plan && SPI_plan_is_valid(plan) &&
+		SearchPathMatchesCurrentEnvironment(entry->search_path))
+		return plan;
+
+	/*
+	 * Otherwise we might as well flush the cached plan now, to free a little
+	 * memory space before we make a new one.
+	 */
+	if (plan)
+		SPI_freeplan(plan);
+	if (entry->search_path)
+		pfree(entry->search_path);
+
+	entry->plan = NULL;
+	entry->search_path = NULL;
+
+	return NULL;
+}
+
+/*
+ * mv_HashPreparedPlan
+ *
+ * Add another plan to our private SPI query plan hashtable.
+ */
+static void
+mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan)
+{
+	MV_QueryHashEntry *entry;
+	bool		found;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Add the new plan.  We might be overwriting an entry previously found
+	 * invalid by mv_FetchPreparedPlan.
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_ENTER, &found);
+	Assert(!found || entry->plan == NULL);
+	entry->plan = plan;
+	entry->search_path = GetSearchPathMatcher(TopMemoryContext);
+}
+
+/*
+ * mv_BuildQueryKey
+ *
+ * Construct a hashtable key for a prepared SPI plan for IVM.
+ */
+static void
+mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type)
+{
+	/*
+	 * We assume struct MV_QueryKey contains no padding bytes, else we'd need
+	 * to use memset to clear them.
+	 */
+	key->matview_id = matview_id;
+	key->query_type = query_type;
+}
+
 /*
  * AtAbort_IVM
  *
-- 
2.43.0


--Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd
Content-Type: text/x-diff;
 name="v37-0008-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v37-0008-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 259+ messages in thread

* [PATCH v38 09/11] Add support for min/max aggregates for IVM
@ 2023-05-31 11:58  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 259+ messages in thread

From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw)

Supporting min and max is more complicated than count, sum, or avg.

For an example of min, when tuples are inserted, the current min value
in the view and the min value in the inseteted tuples are compared,
then the smaller one is used as the latest min value. On the other
hand, when tuples are deleted, if the current min value in the view
equals to the min in the deleted tuples, we need re-computation the
latest min value from base tables. Otherwise, the current value in
the view remains.
---
 src/backend/commands/createas.c |  45 +++
 src/backend/commands/matview.c  | 644 +++++++++++++++++++++++++++++++-
 2 files changed, 680 insertions(+), 9 deletions(-)

diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 35e124694ab..540d9e3d5c8 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid)
 		case F_AVG_FLOAT8:
 		case F_AVG_INTERVAL:
 
+		/* min */
+		case F_MIN_ANYARRAY:
+		case F_MIN_INT8:
+		case F_MIN_INT4:
+		case F_MIN_INT2:
+		case F_MIN_OID:
+		case F_MIN_FLOAT4:
+		case F_MIN_FLOAT8:
+		case F_MIN_DATE:
+		case F_MIN_TIME:
+		case F_MIN_TIMETZ:
+		case F_MIN_MONEY:
+		case F_MIN_TIMESTAMP:
+		case F_MIN_TIMESTAMPTZ:
+		case F_MIN_INTERVAL:
+		case F_MIN_TEXT:
+		case F_MIN_NUMERIC:
+		case F_MIN_BPCHAR:
+		case F_MIN_TID:
+		case F_MIN_ANYENUM:
+		case F_MIN_INET:
+		case F_MIN_PG_LSN:
+
+		/* max */
+		case F_MAX_ANYARRAY:
+		case F_MAX_INT8:
+		case F_MAX_INT4:
+		case F_MAX_INT2:
+		case F_MAX_OID:
+		case F_MAX_FLOAT4:
+		case F_MAX_FLOAT8:
+		case F_MAX_DATE:
+		case F_MAX_TIME:
+		case F_MAX_TIMETZ:
+		case F_MAX_MONEY:
+		case F_MAX_TIMESTAMP:
+		case F_MAX_TIMESTAMPTZ:
+		case F_MAX_INTERVAL:
+		case F_MAX_TEXT:
+		case F_MAX_NUMERIC:
+		case F_MAX_BPCHAR:
+		case F_MAX_TID:
+		case F_MAX_ANYENUM:
+		case F_MAX_INET:
+		case F_MAX_PG_LSN:
 			return true;
 
 		default:
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 710224aa994..3b3871c49e2 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -69,6 +69,34 @@ typedef struct
 
 #define MV_INIT_QUERYHASHSIZE	16
 
+/* MV query type codes */
+#define MV_PLAN_RECALC			1
+#define MV_PLAN_SET_VALUE		2
+
+/*
+ * MI_QueryKey
+ *
+ * The key identifying a prepared SPI plan in our query hashtable
+ */
+typedef struct MV_QueryKey
+{
+	Oid			matview_id;	/* OID of materialized view */
+	int32		query_type;	/* query type ID, see MV_PLAN_XXX above */
+} MV_QueryKey;
+
+/*
+ * MV_QueryHashEntry
+ *
+ * Hash entry for cached plans used to maintain materialized views.
+ */
+typedef struct MV_QueryHashEntry
+{
+	MV_QueryKey key;
+	SPIPlanPtr	plan;
+	SearchPathMatcher *search_path;        /* search_path used for parsing
+											 * and planning */
+} MV_QueryHashEntry;
+
 /*
  * MV_TriggerHashEntry
  *
@@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo
 } DroppedImmvInfo;
 
 static HTAB *mv_trigger_info = NULL;
+static HTAB *mv_query_cache = NULL;
 static HTAB *dropped_immv = NULL;
 
 static HTAB *LastIvmUpdateHash;
@@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old,
 static void append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 						  StringInfo buf_new, StringInfo aggs_list,
 						  const char *aggtype);
+static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min);
 static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2,
 					 const char* count_col, const char *castType);
 static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
@@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old,
 				List *keys);
 static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname);
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc);
 static void apply_new_delta(const char *matviewname, const char *deltaname_new,
 				StringInfo target_list);
 static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
 				List *keys, StringInfo target_list, StringInfo aggs_set,
 				const char* count_colname);
 static char *get_matching_condition_string(List *keys);
+static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys);
+static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list);
+static char *get_select_for_recalc_string(List *keys);
+static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel);
+static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes);
+static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes);
 static void generate_equal(StringInfo querybuf, Oid opttype,
 			   const char *leftop, const char *rightop);
 
 static void mv_InitHashTables(void);
+static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key);
+static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan);
+static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type);
 static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
 									SubTransactionId subxid);
 static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
@@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	ListCell	*lc;
 	int			i;
 	List	   *keys = NIL;
+	List	   *minmax_list = NIL;
+	List	   *is_min_list = NIL;
 
 
 	/*
@@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 				append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf,
 										  format_type_be(aggref->aggtype));
 
+			/* min/max */
+			else if (!strcmp(aggname, "min") || !strcmp(aggname, "max"))
+			{
+				bool	is_min = (!strcmp(aggname, "min"));
+
+				append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min);
+
+				/* make a resname list of min and max aggregates */
+				minmax_list = lappend(minmax_list, resname);
+				is_min_list = lappend_int(is_min_list, is_min);
+			}
 			else
 				elog(ERROR, "unsupported aggregate function: %s", aggname);
 		}
@@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
 	{
 		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		SPITupleTable  *tuptable_recalc = NULL;
+		uint64			num_recalc;
 		int				rc;
 
 		/* convert tuplestores to ENR, and register for SPI */
@@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 			/* apply old delta and get rows to be recalculated */
 			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
 									   keys, aggs_list_buf, aggs_set_old,
-									   count_colname);
+									   minmax_list, is_min_list,
+									   count_colname, &tuptable_recalc, &num_recalc);
 		else
 			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
 
+		/*
+		 * If we have min or max, we might have to recalculate aggregate values from base tables
+		 * on some tuples. TIDs and keys such tuples are returned as a result of the above query.
+		 */
+		if (minmax_list && tuptable_recalc)
+			recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel);
+
 	}
 	/* For tuple insertion */
 	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
@@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 	);
 }
 
+/*
+ * append_set_clause_for_minmax
+ *
+ * Append SET clause string for min or max aggregation to given buffers.
+ * Also, append resnames required for calculating the aggregate value.
+ * is_min is true if this is min, false if not.
+ */
+static void
+append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min)
+{
+	char *count_col = IVM_colname("count", resname);
+
+	/* For tuple deletion */
+	if (buf_old)
+	{
+		/*
+		 * If the new value doesn't became NULL then use the value remaining
+		 * in the view although this will be recomputated afterwords.
+		 */
+		appendStringInfo(buf_old,
+			", %s = CASE WHEN %s THEN NULL ELSE %s END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_SUB, "mv", "t", count_col),
+			quote_qualified_identifier("mv", resname)
+		);
+		/* count = mv.count - t.count */
+		appendStringInfo(buf_old,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL)
+		);
+	}
+	/* For tuple insertion */
+	if (buf_new)
+	{
+		/*
+		 * min = LEAST(mv.min, diff.min)
+		 * max = GREATEST(mv.max, diff.max)
+		 */
+		appendStringInfo(buf_new,
+			", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_ADD, "mv", "diff", count_col),
+
+			is_min ? "LEAST" : "GREATEST",
+			quote_qualified_identifier("mv", resname),
+			quote_qualified_identifier("diff", resname)
+		);
+		/* count = mv.count + diff.count */
+		appendStringInfo(buf_new,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL)
+		);
+	}
+
+	appendStringInfo(aggs_list, ", %s, %s",
+		quote_qualified_identifier("diff", resname),
+		quote_qualified_identifier("diff", IVM_colname("count", resname))
+	);
+}
+
 /*
  * get_operation_string
  *
@@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
  * list to identify a tuple in the view. If the view has aggregates, this
  * requires strings representing resnames of aggregates and SET clause for
  * updating aggregate values.
+ *
+ * If the view has min or max aggregate, this requires a list of resnames of
+ * min/max aggregates and a list of boolean which represents which entries in
+ * minmax_list is min. These are necessary to check if we need to recalculate
+ * min or max aggregate values. In this case, this query returns TID and keys
+ * of tuples which need to be recalculated.  This result and the number of rows
+ * are stored in tuptables and num_recalc repectedly.
+ *
  */
 static void
 apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname)
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc)
 {
 	StringInfoData	querybuf;
 	char   *match_cond;
+	char   *updt_returning = "";
+	char   *select_for_recalc = "SELECT";
 	bool	agg_without_groupby = (list_length(keys) == 0);
 
+	Assert(tuptable_recalc != NULL);
+	Assert(num_recalc != NULL);
+
 	/* build WHERE condition for searching tuples to be deleted */
 	match_cond = get_matching_condition_string(keys);
 
+	/*
+	 * We need a special RETURNING clause and SELECT statement for min/max to
+	 * check which tuple needs re-calculation from base tables.
+	 */
+	if (minmax_list)
+	{
+		updt_returning = get_returning_string(minmax_list, is_min_list, keys);
+		select_for_recalc = get_select_for_recalc_string(keys);
+	}
+
 	/* Search for matching tuples from the view and update or delete if found. */
 	initStringInfo(&querybuf);
 	appendStringInfo(&querybuf,
@@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
 											"%s"	/* SET clauses for aggregates */
 						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
-					")"
-					/* delete a tuple if this is to be deleted */
-					"DELETE FROM %s AS mv USING t "
-					"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt",
+						"%s"						/* RETURNING clause for recalc infomation */
+					"), dlt AS ("			/* delete a tuple if this is to be deleted */
+						"DELETE FROM %s AS mv USING t "
+						"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt"
+					") %s",							/* SELECT returning which tuples need to be recalculated */
 					count_colname,
 					count_colname, count_colname, (agg_without_groupby ? "false" : "true"),
 					(aggs_list != NULL ? aggs_list->data : ""),
@@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 					match_cond,
 					matviewname, count_colname, count_colname, count_colname,
 					(aggs_set != NULL ? aggs_set->data : ""),
-					matviewname);
+					updt_returning,
+					matviewname,
+					select_for_recalc);
 
-	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT)
 		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+
+
+	/* Return tuples to be recalculated. */
+	if (minmax_list)
+	{
+		*tuptable_recalc = SPI_tuptable;
+		*num_recalc = SPI_processed;
+	}
+	else
+	{
+		*tuptable_recalc = NULL;
+		*num_recalc = 0;
+	}
 }
 
 /*
@@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys)
 	return match_cond.data;
 }
 
+/*
+ * get_returning_string
+ *
+ * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count.
+ * This clause returns ctid and a boolean value that indicates if we need to
+ * recalculate min or max value, for each updated row.
+ */
+static char *
+get_returning_string(List *minmax_list, List *is_min_list, List *keys)
+{
+	StringInfoData returning;
+	char		*recalc_cond;
+	ListCell	*lc;
+
+	Assert(minmax_list != NIL && is_min_list != NIL);
+	recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list);
+
+	initStringInfo(&returning);
+
+	appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char *resname = NameStr(attr->attname);
+		appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname));
+	}
+
+	return returning.data;
+}
+
+/*
+ * get_minmax_recalc_condition_string
+ *
+ * Build a predicate string for checking if any min/max aggregate
+ * value needs to be recalculated.
+ */
+static char *
+get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list)
+{
+	StringInfoData recalc_cond;
+	ListCell	*lc1, *lc2;
+
+	initStringInfo(&recalc_cond);
+
+	Assert (list_length(minmax_list) == list_length(is_min_list));
+
+	forboth (lc1, minmax_list, lc2, is_min_list)
+	{
+		char   *resname = (char *) lfirst(lc1);
+		bool	is_min = (bool) lfirst_int(lc2);
+		char   *op_str = (is_min ? ">=" : "<=");
+
+		appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s",
+			quote_qualified_identifier("mv", resname),
+			op_str,
+			quote_qualified_identifier("t", resname)
+		);
+
+		if (lnext(minmax_list, lc1))
+			appendStringInfo(&recalc_cond, " OR ");
+	}
+
+	return recalc_cond.data;
+}
+
+/*
+ * get_select_for_recalc_string
+ *
+ * Build a query to return tid and keys of tuples which need
+ * recalculation. This is used as the result of the query
+ * built by apply_old_delta.
+ */
+static char *
+get_select_for_recalc_string(List *keys)
+{
+	StringInfoData qry;
+	ListCell	*lc;
+
+	initStringInfo(&qry);
+
+	appendStringInfo(&qry, "SELECT tid");
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		appendStringInfo(&qry, ", %s", NameStr(attr->attname));
+	}
+
+	appendStringInfo(&qry, " FROM updt WHERE recalc");
+
+	return qry.data;
+}
+
+/*
+ * recalc_and_set_values
+ *
+ * Recalculate tuples in a materialized from base tables and update these.
+ * The tuples which needs recalculation are specified by keys, and resnames
+ * of columns to be updated are specified by namelist. TIDs and key values
+ * are given by tuples in tuptable_recalc. Its first attribute must be TID
+ * and key values must be following this.
+ */
+static void
+recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel)
+{
+	TupleDesc   tupdesc_recalc = tuptable_recalc->tupdesc;
+	Oid		   *keyTypes = NULL, *types = NULL;
+	char	   *keyNulls = NULL, *nulls = NULL;
+	Datum	   *keyVals = NULL, *vals = NULL;
+	int			num_vals = list_length(namelist);
+	int			num_keys = list_length(keys);
+	uint64      i;
+	Oid			matviewOid;
+	char	   *matviewname;
+
+	matviewOid = RelationGetRelid(matviewRel);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/* If we have keys, initialize arrays for them. */
+	if (keys)
+	{
+		keyTypes = palloc(sizeof(Oid) * num_keys);
+		keyNulls = palloc(sizeof(char) * num_keys);
+		keyVals = palloc(sizeof(Datum) * num_keys);
+		/* a tuple contains keys to be recalculated and ctid to be updated*/
+		Assert(tupdesc_recalc->natts == num_keys + 1);
+
+		/* Types of key attributes  */
+		for (i = 0; i < num_keys; i++)
+			keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid;
+	}
+
+	/* allocate memory for all attribute names and tid */
+	types = palloc(sizeof(Oid) * (num_vals + 1));
+	nulls = palloc(sizeof(char) * (num_vals + 1));
+	vals = palloc(sizeof(Datum) * (num_vals + 1));
+
+	/* For each tuple which needs recalculation */
+	for (i = 0; i < num_tuples; i++)
+	{
+		int j;
+		bool isnull;
+		SPIPlanPtr plan;
+		SPITupleTable *tuptable_newvals;
+		TupleDesc   tupdesc_newvals;
+
+		/* Set group key values as parameters if needed. */
+		if (keys)
+		{
+			for (j = 0; j < num_keys; j++)
+			{
+				keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull);
+				if (isnull)
+					keyNulls[j] = 'n';
+				else
+					keyNulls[j] = ' ';
+			}
+		}
+
+		/*
+		 * Get recalculated values from base tables. The result must be
+		 * only one tuple thich contains the new values for specified keys.
+		 */
+		plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes);
+		if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT)
+			elog(ERROR, "SPI_execute_plan");
+		if (SPI_processed != 1)
+			elog(ERROR, "SPI_execute_plan returned zero or more than one rows");
+
+		tuptable_newvals = SPI_tuptable;
+		tupdesc_newvals = tuptable_newvals->tupdesc;
+
+		Assert(tupdesc_newvals->natts == num_vals);
+
+		/* Set the new values as parameters */
+		for (j = 0; j < tupdesc_newvals->natts; j++)
+		{
+			if (i == 0)
+				types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid;
+
+			vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull);
+			if (isnull)
+				nulls[j] = 'n';
+			else
+				nulls[j] = ' ';
+		}
+		/* Set TID of the view tuple to be updated as a parameter */
+		types[j] = TIDOID;
+		vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull);
+		nulls[j] = ' ';
+
+		/* Update the view tuple to the new values */
+		plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types);
+		if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE)
+			elog(ERROR, "SPI_execute_plan");
+	}
+}
+
+
+/*
+ * get_plan_for_recalc
+ *
+ * Create or fetch a plan for recalculating value in the view's target list
+ * from base tables using the definition query of materialized view specified
+ * by matviewOid. namelist is a list of resnames of values to be recalculated.
+ *
+ * keys is a list of keys to identify tuples to be recalculated if this is not
+ * empty. KeyTypes is an array of types of keys.
+ */
+static SPIPlanPtr
+get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes)
+{
+	MV_QueryKey hash_key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the recalculation */
+	mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC);
+	if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL)
+	{
+		ListCell	   *lc;
+		StringInfoData	str;
+		char   *viewdef;
+
+		/* get view definition of matview */
+		viewdef = text_to_cstring((text *) DatumGetPointer(
+					DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid))));
+		/* get rid of trailing semi-colon */
+		viewdef[strlen(viewdef)-1] = '\0';
+
+		/*
+		 * Build a query string for recalculating values. This is like
+		 *
+		 *  SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv
+		 *   WHERE (key1, key2, ...) = ($1, $2, ...);
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "SELECT ");
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, " FROM (%s) mv", viewdef);
+
+		if (keys)
+		{
+			int		i = 1;
+			char	paramname[16];
+
+			appendStringInfo(&str, " WHERE (");
+			foreach (lc, keys)
+			{
+				Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+				char   *resname = NameStr(attr->attname);
+				Oid		typid = attr->atttypid;
+
+				sprintf(paramname, "$%d", i);
+				appendStringInfo(&str, "(");
+				generate_equal(&str, typid, resname, paramname);
+				appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))",
+								 resname, paramname);
+
+				if (lnext(keys, lc))
+					appendStringInfoString(&str, " AND ");
+				i++;
+			}
+			appendStringInfo(&str, ")");
+		}
+		else
+			keyTypes = NULL;
+
+		plan = SPI_prepare(str.data, list_length(keys), keyTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&hash_key, plan);
+	}
+
+	return plan;
+}
+
+/*
+ * get_plan_for_set_values
+ *
+ * Create or fetch a plan for applying new values calculated by
+ * get_plan_for_recalc to a materialized view specified by matviewOid.
+ * matviewname is the name of the view.  namelist is a list of resnames
+ * of attributes to be updated, and valTypes is an array of types of the
+ * values.
+ */
+static SPIPlanPtr
+get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes)
+{
+	MV_QueryKey	key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the real check */
+	mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE);
+	if ((plan = mv_FetchPreparedPlan(&key)) == NULL)
+	{
+		ListCell	  *lc;
+		StringInfoData str;
+		int		i;
+
+		/*
+		 * Build a query string for applying min/max values. This is like
+		 *
+		 *  UPDATE matviewname AS mv
+		 *   SET (x1, x2, x3, x4) = ($1, $2, $3, $4)
+		 *   WHERE ctid = $5;
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname);
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, ") = ROW(");
+
+		for (i = 1; i <= list_length(namelist); i++)
+			appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i);
+
+		appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i);
+
+		plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&key, plan);
+	}
+
+	return plan;
+}
+
 /*
  * generate_equals
  *
@@ -3025,6 +3541,13 @@ mv_InitHashTables(void)
 {
 	HASHCTL		ctl;
 
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(MV_QueryKey);
+	ctl.entrysize = sizeof(MV_QueryHashEntry);
+	mv_query_cache = hash_create("MV query cache",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
 	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(MV_TriggerHashEntry);
@@ -3039,6 +3562,109 @@ mv_InitHashTables(void)
 							   &ctl, HASH_ELEM | HASH_BLOBS);
 }
 
+/*
+ * mv_FetchPreparedPlan
+ */
+static SPIPlanPtr
+mv_FetchPreparedPlan(MV_QueryKey *key)
+{
+	MV_QueryHashEntry *entry;
+	SPIPlanPtr	plan;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Lookup for the key
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_FIND, NULL);
+	if (entry == NULL)
+		return NULL;
+
+	/*
+	 * Check whether the plan is still valid.  If it isn't, we don't want to
+	 * simply rely on plancache.c to regenerate it; rather we should start
+	 * from scratch and rebuild the query text too.  This is to cover cases
+	 * such as table/column renames.  We depend on the plancache machinery to
+	 * detect possible invalidations, though.
+	 *
+	 * CAUTION: this check is only trustworthy if the caller has already
+	 * locked both materialized views and base tables.
+	 *
+	 * Also, check whether the search_path is still the same as when we made it.
+	 * If it isn't, we need to rebuild the query text because the result of
+	 * pg_ivm_get_viewdef() will change.
+	 */
+	plan = entry->plan;
+	if (plan && SPI_plan_is_valid(plan) &&
+		SearchPathMatchesCurrentEnvironment(entry->search_path))
+		return plan;
+
+	/*
+	 * Otherwise we might as well flush the cached plan now, to free a little
+	 * memory space before we make a new one.
+	 */
+	if (plan)
+		SPI_freeplan(plan);
+	if (entry->search_path)
+		pfree(entry->search_path);
+
+	entry->plan = NULL;
+	entry->search_path = NULL;
+
+	return NULL;
+}
+
+/*
+ * mv_HashPreparedPlan
+ *
+ * Add another plan to our private SPI query plan hashtable.
+ */
+static void
+mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan)
+{
+	MV_QueryHashEntry *entry;
+	bool		found;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Add the new plan.  We might be overwriting an entry previously found
+	 * invalid by mv_FetchPreparedPlan.
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_ENTER, &found);
+	Assert(!found || entry->plan == NULL);
+	entry->plan = plan;
+	entry->search_path = GetSearchPathMatcher(TopMemoryContext);
+}
+
+/*
+ * mv_BuildQueryKey
+ *
+ * Construct a hashtable key for a prepared SPI plan for IVM.
+ */
+static void
+mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type)
+{
+	/*
+	 * We assume struct MV_QueryKey contains no padding bytes, else we'd need
+	 * to use memset to clear them.
+	 */
+	key->matview_id = matview_id;
+	key->query_type = query_type;
+}
+
 /*
  * AtAbort_IVM
  *
-- 
2.43.0


--Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ
Content-Type: text/x-diff;
 name="v38-0008-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v38-0008-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 259+ messages in thread

* [PATCH v37 09/11] Add support for min/max aggregates for IVM
@ 2023-05-31 11:58  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 259+ messages in thread

From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw)

Supporting min and max is more complicated than count, sum, or avg.

For an example of min, when tuples are inserted, the current min value
in the view and the min value in the inseteted tuples are compared,
then the smaller one is used as the latest min value. On the other
hand, when tuples are deleted, if the current min value in the view
equals to the min in the deleted tuples, we need re-computation the
latest min value from base tables. Otherwise, the current value in
the view remains.
---
 src/backend/commands/createas.c |  45 +++
 src/backend/commands/matview.c  | 644 +++++++++++++++++++++++++++++++-
 2 files changed, 680 insertions(+), 9 deletions(-)

diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 45a30309951..ed67f399b7c 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid)
 		case F_AVG_FLOAT8:
 		case F_AVG_INTERVAL:
 
+		/* min */
+		case F_MIN_ANYARRAY:
+		case F_MIN_INT8:
+		case F_MIN_INT4:
+		case F_MIN_INT2:
+		case F_MIN_OID:
+		case F_MIN_FLOAT4:
+		case F_MIN_FLOAT8:
+		case F_MIN_DATE:
+		case F_MIN_TIME:
+		case F_MIN_TIMETZ:
+		case F_MIN_MONEY:
+		case F_MIN_TIMESTAMP:
+		case F_MIN_TIMESTAMPTZ:
+		case F_MIN_INTERVAL:
+		case F_MIN_TEXT:
+		case F_MIN_NUMERIC:
+		case F_MIN_BPCHAR:
+		case F_MIN_TID:
+		case F_MIN_ANYENUM:
+		case F_MIN_INET:
+		case F_MIN_PG_LSN:
+
+		/* max */
+		case F_MAX_ANYARRAY:
+		case F_MAX_INT8:
+		case F_MAX_INT4:
+		case F_MAX_INT2:
+		case F_MAX_OID:
+		case F_MAX_FLOAT4:
+		case F_MAX_FLOAT8:
+		case F_MAX_DATE:
+		case F_MAX_TIME:
+		case F_MAX_TIMETZ:
+		case F_MAX_MONEY:
+		case F_MAX_TIMESTAMP:
+		case F_MAX_TIMESTAMPTZ:
+		case F_MAX_INTERVAL:
+		case F_MAX_TEXT:
+		case F_MAX_NUMERIC:
+		case F_MAX_BPCHAR:
+		case F_MAX_TID:
+		case F_MAX_ANYENUM:
+		case F_MAX_INET:
+		case F_MAX_PG_LSN:
 			return true;
 
 		default:
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 710224aa994..3b3871c49e2 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -69,6 +69,34 @@ typedef struct
 
 #define MV_INIT_QUERYHASHSIZE	16
 
+/* MV query type codes */
+#define MV_PLAN_RECALC			1
+#define MV_PLAN_SET_VALUE		2
+
+/*
+ * MI_QueryKey
+ *
+ * The key identifying a prepared SPI plan in our query hashtable
+ */
+typedef struct MV_QueryKey
+{
+	Oid			matview_id;	/* OID of materialized view */
+	int32		query_type;	/* query type ID, see MV_PLAN_XXX above */
+} MV_QueryKey;
+
+/*
+ * MV_QueryHashEntry
+ *
+ * Hash entry for cached plans used to maintain materialized views.
+ */
+typedef struct MV_QueryHashEntry
+{
+	MV_QueryKey key;
+	SPIPlanPtr	plan;
+	SearchPathMatcher *search_path;        /* search_path used for parsing
+											 * and planning */
+} MV_QueryHashEntry;
+
 /*
  * MV_TriggerHashEntry
  *
@@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo
 } DroppedImmvInfo;
 
 static HTAB *mv_trigger_info = NULL;
+static HTAB *mv_query_cache = NULL;
 static HTAB *dropped_immv = NULL;
 
 static HTAB *LastIvmUpdateHash;
@@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old,
 static void append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 						  StringInfo buf_new, StringInfo aggs_list,
 						  const char *aggtype);
+static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min);
 static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2,
 					 const char* count_col, const char *castType);
 static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
@@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old,
 				List *keys);
 static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname);
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc);
 static void apply_new_delta(const char *matviewname, const char *deltaname_new,
 				StringInfo target_list);
 static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
 				List *keys, StringInfo target_list, StringInfo aggs_set,
 				const char* count_colname);
 static char *get_matching_condition_string(List *keys);
+static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys);
+static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list);
+static char *get_select_for_recalc_string(List *keys);
+static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel);
+static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes);
+static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes);
 static void generate_equal(StringInfo querybuf, Oid opttype,
 			   const char *leftop, const char *rightop);
 
 static void mv_InitHashTables(void);
+static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key);
+static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan);
+static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type);
 static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
 									SubTransactionId subxid);
 static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
@@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	ListCell	*lc;
 	int			i;
 	List	   *keys = NIL;
+	List	   *minmax_list = NIL;
+	List	   *is_min_list = NIL;
 
 
 	/*
@@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 				append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf,
 										  format_type_be(aggref->aggtype));
 
+			/* min/max */
+			else if (!strcmp(aggname, "min") || !strcmp(aggname, "max"))
+			{
+				bool	is_min = (!strcmp(aggname, "min"));
+
+				append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min);
+
+				/* make a resname list of min and max aggregates */
+				minmax_list = lappend(minmax_list, resname);
+				is_min_list = lappend_int(is_min_list, is_min);
+			}
 			else
 				elog(ERROR, "unsupported aggregate function: %s", aggname);
 		}
@@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
 	{
 		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		SPITupleTable  *tuptable_recalc = NULL;
+		uint64			num_recalc;
 		int				rc;
 
 		/* convert tuplestores to ENR, and register for SPI */
@@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 			/* apply old delta and get rows to be recalculated */
 			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
 									   keys, aggs_list_buf, aggs_set_old,
-									   count_colname);
+									   minmax_list, is_min_list,
+									   count_colname, &tuptable_recalc, &num_recalc);
 		else
 			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
 
+		/*
+		 * If we have min or max, we might have to recalculate aggregate values from base tables
+		 * on some tuples. TIDs and keys such tuples are returned as a result of the above query.
+		 */
+		if (minmax_list && tuptable_recalc)
+			recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel);
+
 	}
 	/* For tuple insertion */
 	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
@@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 	);
 }
 
+/*
+ * append_set_clause_for_minmax
+ *
+ * Append SET clause string for min or max aggregation to given buffers.
+ * Also, append resnames required for calculating the aggregate value.
+ * is_min is true if this is min, false if not.
+ */
+static void
+append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min)
+{
+	char *count_col = IVM_colname("count", resname);
+
+	/* For tuple deletion */
+	if (buf_old)
+	{
+		/*
+		 * If the new value doesn't became NULL then use the value remaining
+		 * in the view although this will be recomputated afterwords.
+		 */
+		appendStringInfo(buf_old,
+			", %s = CASE WHEN %s THEN NULL ELSE %s END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_SUB, "mv", "t", count_col),
+			quote_qualified_identifier("mv", resname)
+		);
+		/* count = mv.count - t.count */
+		appendStringInfo(buf_old,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL)
+		);
+	}
+	/* For tuple insertion */
+	if (buf_new)
+	{
+		/*
+		 * min = LEAST(mv.min, diff.min)
+		 * max = GREATEST(mv.max, diff.max)
+		 */
+		appendStringInfo(buf_new,
+			", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_ADD, "mv", "diff", count_col),
+
+			is_min ? "LEAST" : "GREATEST",
+			quote_qualified_identifier("mv", resname),
+			quote_qualified_identifier("diff", resname)
+		);
+		/* count = mv.count + diff.count */
+		appendStringInfo(buf_new,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL)
+		);
+	}
+
+	appendStringInfo(aggs_list, ", %s, %s",
+		quote_qualified_identifier("diff", resname),
+		quote_qualified_identifier("diff", IVM_colname("count", resname))
+	);
+}
+
 /*
  * get_operation_string
  *
@@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
  * list to identify a tuple in the view. If the view has aggregates, this
  * requires strings representing resnames of aggregates and SET clause for
  * updating aggregate values.
+ *
+ * If the view has min or max aggregate, this requires a list of resnames of
+ * min/max aggregates and a list of boolean which represents which entries in
+ * minmax_list is min. These are necessary to check if we need to recalculate
+ * min or max aggregate values. In this case, this query returns TID and keys
+ * of tuples which need to be recalculated.  This result and the number of rows
+ * are stored in tuptables and num_recalc repectedly.
+ *
  */
 static void
 apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname)
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc)
 {
 	StringInfoData	querybuf;
 	char   *match_cond;
+	char   *updt_returning = "";
+	char   *select_for_recalc = "SELECT";
 	bool	agg_without_groupby = (list_length(keys) == 0);
 
+	Assert(tuptable_recalc != NULL);
+	Assert(num_recalc != NULL);
+
 	/* build WHERE condition for searching tuples to be deleted */
 	match_cond = get_matching_condition_string(keys);
 
+	/*
+	 * We need a special RETURNING clause and SELECT statement for min/max to
+	 * check which tuple needs re-calculation from base tables.
+	 */
+	if (minmax_list)
+	{
+		updt_returning = get_returning_string(minmax_list, is_min_list, keys);
+		select_for_recalc = get_select_for_recalc_string(keys);
+	}
+
 	/* Search for matching tuples from the view and update or delete if found. */
 	initStringInfo(&querybuf);
 	appendStringInfo(&querybuf,
@@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
 											"%s"	/* SET clauses for aggregates */
 						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
-					")"
-					/* delete a tuple if this is to be deleted */
-					"DELETE FROM %s AS mv USING t "
-					"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt",
+						"%s"						/* RETURNING clause for recalc infomation */
+					"), dlt AS ("			/* delete a tuple if this is to be deleted */
+						"DELETE FROM %s AS mv USING t "
+						"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt"
+					") %s",							/* SELECT returning which tuples need to be recalculated */
 					count_colname,
 					count_colname, count_colname, (agg_without_groupby ? "false" : "true"),
 					(aggs_list != NULL ? aggs_list->data : ""),
@@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 					match_cond,
 					matviewname, count_colname, count_colname, count_colname,
 					(aggs_set != NULL ? aggs_set->data : ""),
-					matviewname);
+					updt_returning,
+					matviewname,
+					select_for_recalc);
 
-	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT)
 		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+
+
+	/* Return tuples to be recalculated. */
+	if (minmax_list)
+	{
+		*tuptable_recalc = SPI_tuptable;
+		*num_recalc = SPI_processed;
+	}
+	else
+	{
+		*tuptable_recalc = NULL;
+		*num_recalc = 0;
+	}
 }
 
 /*
@@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys)
 	return match_cond.data;
 }
 
+/*
+ * get_returning_string
+ *
+ * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count.
+ * This clause returns ctid and a boolean value that indicates if we need to
+ * recalculate min or max value, for each updated row.
+ */
+static char *
+get_returning_string(List *minmax_list, List *is_min_list, List *keys)
+{
+	StringInfoData returning;
+	char		*recalc_cond;
+	ListCell	*lc;
+
+	Assert(minmax_list != NIL && is_min_list != NIL);
+	recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list);
+
+	initStringInfo(&returning);
+
+	appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char *resname = NameStr(attr->attname);
+		appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname));
+	}
+
+	return returning.data;
+}
+
+/*
+ * get_minmax_recalc_condition_string
+ *
+ * Build a predicate string for checking if any min/max aggregate
+ * value needs to be recalculated.
+ */
+static char *
+get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list)
+{
+	StringInfoData recalc_cond;
+	ListCell	*lc1, *lc2;
+
+	initStringInfo(&recalc_cond);
+
+	Assert (list_length(minmax_list) == list_length(is_min_list));
+
+	forboth (lc1, minmax_list, lc2, is_min_list)
+	{
+		char   *resname = (char *) lfirst(lc1);
+		bool	is_min = (bool) lfirst_int(lc2);
+		char   *op_str = (is_min ? ">=" : "<=");
+
+		appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s",
+			quote_qualified_identifier("mv", resname),
+			op_str,
+			quote_qualified_identifier("t", resname)
+		);
+
+		if (lnext(minmax_list, lc1))
+			appendStringInfo(&recalc_cond, " OR ");
+	}
+
+	return recalc_cond.data;
+}
+
+/*
+ * get_select_for_recalc_string
+ *
+ * Build a query to return tid and keys of tuples which need
+ * recalculation. This is used as the result of the query
+ * built by apply_old_delta.
+ */
+static char *
+get_select_for_recalc_string(List *keys)
+{
+	StringInfoData qry;
+	ListCell	*lc;
+
+	initStringInfo(&qry);
+
+	appendStringInfo(&qry, "SELECT tid");
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		appendStringInfo(&qry, ", %s", NameStr(attr->attname));
+	}
+
+	appendStringInfo(&qry, " FROM updt WHERE recalc");
+
+	return qry.data;
+}
+
+/*
+ * recalc_and_set_values
+ *
+ * Recalculate tuples in a materialized from base tables and update these.
+ * The tuples which needs recalculation are specified by keys, and resnames
+ * of columns to be updated are specified by namelist. TIDs and key values
+ * are given by tuples in tuptable_recalc. Its first attribute must be TID
+ * and key values must be following this.
+ */
+static void
+recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel)
+{
+	TupleDesc   tupdesc_recalc = tuptable_recalc->tupdesc;
+	Oid		   *keyTypes = NULL, *types = NULL;
+	char	   *keyNulls = NULL, *nulls = NULL;
+	Datum	   *keyVals = NULL, *vals = NULL;
+	int			num_vals = list_length(namelist);
+	int			num_keys = list_length(keys);
+	uint64      i;
+	Oid			matviewOid;
+	char	   *matviewname;
+
+	matviewOid = RelationGetRelid(matviewRel);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/* If we have keys, initialize arrays for them. */
+	if (keys)
+	{
+		keyTypes = palloc(sizeof(Oid) * num_keys);
+		keyNulls = palloc(sizeof(char) * num_keys);
+		keyVals = palloc(sizeof(Datum) * num_keys);
+		/* a tuple contains keys to be recalculated and ctid to be updated*/
+		Assert(tupdesc_recalc->natts == num_keys + 1);
+
+		/* Types of key attributes  */
+		for (i = 0; i < num_keys; i++)
+			keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid;
+	}
+
+	/* allocate memory for all attribute names and tid */
+	types = palloc(sizeof(Oid) * (num_vals + 1));
+	nulls = palloc(sizeof(char) * (num_vals + 1));
+	vals = palloc(sizeof(Datum) * (num_vals + 1));
+
+	/* For each tuple which needs recalculation */
+	for (i = 0; i < num_tuples; i++)
+	{
+		int j;
+		bool isnull;
+		SPIPlanPtr plan;
+		SPITupleTable *tuptable_newvals;
+		TupleDesc   tupdesc_newvals;
+
+		/* Set group key values as parameters if needed. */
+		if (keys)
+		{
+			for (j = 0; j < num_keys; j++)
+			{
+				keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull);
+				if (isnull)
+					keyNulls[j] = 'n';
+				else
+					keyNulls[j] = ' ';
+			}
+		}
+
+		/*
+		 * Get recalculated values from base tables. The result must be
+		 * only one tuple thich contains the new values for specified keys.
+		 */
+		plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes);
+		if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT)
+			elog(ERROR, "SPI_execute_plan");
+		if (SPI_processed != 1)
+			elog(ERROR, "SPI_execute_plan returned zero or more than one rows");
+
+		tuptable_newvals = SPI_tuptable;
+		tupdesc_newvals = tuptable_newvals->tupdesc;
+
+		Assert(tupdesc_newvals->natts == num_vals);
+
+		/* Set the new values as parameters */
+		for (j = 0; j < tupdesc_newvals->natts; j++)
+		{
+			if (i == 0)
+				types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid;
+
+			vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull);
+			if (isnull)
+				nulls[j] = 'n';
+			else
+				nulls[j] = ' ';
+		}
+		/* Set TID of the view tuple to be updated as a parameter */
+		types[j] = TIDOID;
+		vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull);
+		nulls[j] = ' ';
+
+		/* Update the view tuple to the new values */
+		plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types);
+		if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE)
+			elog(ERROR, "SPI_execute_plan");
+	}
+}
+
+
+/*
+ * get_plan_for_recalc
+ *
+ * Create or fetch a plan for recalculating value in the view's target list
+ * from base tables using the definition query of materialized view specified
+ * by matviewOid. namelist is a list of resnames of values to be recalculated.
+ *
+ * keys is a list of keys to identify tuples to be recalculated if this is not
+ * empty. KeyTypes is an array of types of keys.
+ */
+static SPIPlanPtr
+get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes)
+{
+	MV_QueryKey hash_key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the recalculation */
+	mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC);
+	if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL)
+	{
+		ListCell	   *lc;
+		StringInfoData	str;
+		char   *viewdef;
+
+		/* get view definition of matview */
+		viewdef = text_to_cstring((text *) DatumGetPointer(
+					DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid))));
+		/* get rid of trailing semi-colon */
+		viewdef[strlen(viewdef)-1] = '\0';
+
+		/*
+		 * Build a query string for recalculating values. This is like
+		 *
+		 *  SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv
+		 *   WHERE (key1, key2, ...) = ($1, $2, ...);
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "SELECT ");
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, " FROM (%s) mv", viewdef);
+
+		if (keys)
+		{
+			int		i = 1;
+			char	paramname[16];
+
+			appendStringInfo(&str, " WHERE (");
+			foreach (lc, keys)
+			{
+				Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+				char   *resname = NameStr(attr->attname);
+				Oid		typid = attr->atttypid;
+
+				sprintf(paramname, "$%d", i);
+				appendStringInfo(&str, "(");
+				generate_equal(&str, typid, resname, paramname);
+				appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))",
+								 resname, paramname);
+
+				if (lnext(keys, lc))
+					appendStringInfoString(&str, " AND ");
+				i++;
+			}
+			appendStringInfo(&str, ")");
+		}
+		else
+			keyTypes = NULL;
+
+		plan = SPI_prepare(str.data, list_length(keys), keyTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&hash_key, plan);
+	}
+
+	return plan;
+}
+
+/*
+ * get_plan_for_set_values
+ *
+ * Create or fetch a plan for applying new values calculated by
+ * get_plan_for_recalc to a materialized view specified by matviewOid.
+ * matviewname is the name of the view.  namelist is a list of resnames
+ * of attributes to be updated, and valTypes is an array of types of the
+ * values.
+ */
+static SPIPlanPtr
+get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes)
+{
+	MV_QueryKey	key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the real check */
+	mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE);
+	if ((plan = mv_FetchPreparedPlan(&key)) == NULL)
+	{
+		ListCell	  *lc;
+		StringInfoData str;
+		int		i;
+
+		/*
+		 * Build a query string for applying min/max values. This is like
+		 *
+		 *  UPDATE matviewname AS mv
+		 *   SET (x1, x2, x3, x4) = ($1, $2, $3, $4)
+		 *   WHERE ctid = $5;
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname);
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, ") = ROW(");
+
+		for (i = 1; i <= list_length(namelist); i++)
+			appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i);
+
+		appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i);
+
+		plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&key, plan);
+	}
+
+	return plan;
+}
+
 /*
  * generate_equals
  *
@@ -3025,6 +3541,13 @@ mv_InitHashTables(void)
 {
 	HASHCTL		ctl;
 
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(MV_QueryKey);
+	ctl.entrysize = sizeof(MV_QueryHashEntry);
+	mv_query_cache = hash_create("MV query cache",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
 	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(MV_TriggerHashEntry);
@@ -3039,6 +3562,109 @@ mv_InitHashTables(void)
 							   &ctl, HASH_ELEM | HASH_BLOBS);
 }
 
+/*
+ * mv_FetchPreparedPlan
+ */
+static SPIPlanPtr
+mv_FetchPreparedPlan(MV_QueryKey *key)
+{
+	MV_QueryHashEntry *entry;
+	SPIPlanPtr	plan;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Lookup for the key
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_FIND, NULL);
+	if (entry == NULL)
+		return NULL;
+
+	/*
+	 * Check whether the plan is still valid.  If it isn't, we don't want to
+	 * simply rely on plancache.c to regenerate it; rather we should start
+	 * from scratch and rebuild the query text too.  This is to cover cases
+	 * such as table/column renames.  We depend on the plancache machinery to
+	 * detect possible invalidations, though.
+	 *
+	 * CAUTION: this check is only trustworthy if the caller has already
+	 * locked both materialized views and base tables.
+	 *
+	 * Also, check whether the search_path is still the same as when we made it.
+	 * If it isn't, we need to rebuild the query text because the result of
+	 * pg_ivm_get_viewdef() will change.
+	 */
+	plan = entry->plan;
+	if (plan && SPI_plan_is_valid(plan) &&
+		SearchPathMatchesCurrentEnvironment(entry->search_path))
+		return plan;
+
+	/*
+	 * Otherwise we might as well flush the cached plan now, to free a little
+	 * memory space before we make a new one.
+	 */
+	if (plan)
+		SPI_freeplan(plan);
+	if (entry->search_path)
+		pfree(entry->search_path);
+
+	entry->plan = NULL;
+	entry->search_path = NULL;
+
+	return NULL;
+}
+
+/*
+ * mv_HashPreparedPlan
+ *
+ * Add another plan to our private SPI query plan hashtable.
+ */
+static void
+mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan)
+{
+	MV_QueryHashEntry *entry;
+	bool		found;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Add the new plan.  We might be overwriting an entry previously found
+	 * invalid by mv_FetchPreparedPlan.
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_ENTER, &found);
+	Assert(!found || entry->plan == NULL);
+	entry->plan = plan;
+	entry->search_path = GetSearchPathMatcher(TopMemoryContext);
+}
+
+/*
+ * mv_BuildQueryKey
+ *
+ * Construct a hashtable key for a prepared SPI plan for IVM.
+ */
+static void
+mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type)
+{
+	/*
+	 * We assume struct MV_QueryKey contains no padding bytes, else we'd need
+	 * to use memset to clear them.
+	 */
+	key->matview_id = matview_id;
+	key->query_type = query_type;
+}
+
 /*
  * AtAbort_IVM
  *
-- 
2.43.0


--Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd
Content-Type: text/x-diff;
 name="v37-0008-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v37-0008-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 259+ messages in thread

* [PATCH v38 09/11] Add support for min/max aggregates for IVM
@ 2023-05-31 11:58  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 259+ messages in thread

From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw)

Supporting min and max is more complicated than count, sum, or avg.

For an example of min, when tuples are inserted, the current min value
in the view and the min value in the inseteted tuples are compared,
then the smaller one is used as the latest min value. On the other
hand, when tuples are deleted, if the current min value in the view
equals to the min in the deleted tuples, we need re-computation the
latest min value from base tables. Otherwise, the current value in
the view remains.
---
 src/backend/commands/createas.c |  45 +++
 src/backend/commands/matview.c  | 644 +++++++++++++++++++++++++++++++-
 2 files changed, 680 insertions(+), 9 deletions(-)

diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 35e124694ab..540d9e3d5c8 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid)
 		case F_AVG_FLOAT8:
 		case F_AVG_INTERVAL:
 
+		/* min */
+		case F_MIN_ANYARRAY:
+		case F_MIN_INT8:
+		case F_MIN_INT4:
+		case F_MIN_INT2:
+		case F_MIN_OID:
+		case F_MIN_FLOAT4:
+		case F_MIN_FLOAT8:
+		case F_MIN_DATE:
+		case F_MIN_TIME:
+		case F_MIN_TIMETZ:
+		case F_MIN_MONEY:
+		case F_MIN_TIMESTAMP:
+		case F_MIN_TIMESTAMPTZ:
+		case F_MIN_INTERVAL:
+		case F_MIN_TEXT:
+		case F_MIN_NUMERIC:
+		case F_MIN_BPCHAR:
+		case F_MIN_TID:
+		case F_MIN_ANYENUM:
+		case F_MIN_INET:
+		case F_MIN_PG_LSN:
+
+		/* max */
+		case F_MAX_ANYARRAY:
+		case F_MAX_INT8:
+		case F_MAX_INT4:
+		case F_MAX_INT2:
+		case F_MAX_OID:
+		case F_MAX_FLOAT4:
+		case F_MAX_FLOAT8:
+		case F_MAX_DATE:
+		case F_MAX_TIME:
+		case F_MAX_TIMETZ:
+		case F_MAX_MONEY:
+		case F_MAX_TIMESTAMP:
+		case F_MAX_TIMESTAMPTZ:
+		case F_MAX_INTERVAL:
+		case F_MAX_TEXT:
+		case F_MAX_NUMERIC:
+		case F_MAX_BPCHAR:
+		case F_MAX_TID:
+		case F_MAX_ANYENUM:
+		case F_MAX_INET:
+		case F_MAX_PG_LSN:
 			return true;
 
 		default:
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 710224aa994..3b3871c49e2 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -69,6 +69,34 @@ typedef struct
 
 #define MV_INIT_QUERYHASHSIZE	16
 
+/* MV query type codes */
+#define MV_PLAN_RECALC			1
+#define MV_PLAN_SET_VALUE		2
+
+/*
+ * MI_QueryKey
+ *
+ * The key identifying a prepared SPI plan in our query hashtable
+ */
+typedef struct MV_QueryKey
+{
+	Oid			matview_id;	/* OID of materialized view */
+	int32		query_type;	/* query type ID, see MV_PLAN_XXX above */
+} MV_QueryKey;
+
+/*
+ * MV_QueryHashEntry
+ *
+ * Hash entry for cached plans used to maintain materialized views.
+ */
+typedef struct MV_QueryHashEntry
+{
+	MV_QueryKey key;
+	SPIPlanPtr	plan;
+	SearchPathMatcher *search_path;        /* search_path used for parsing
+											 * and planning */
+} MV_QueryHashEntry;
+
 /*
  * MV_TriggerHashEntry
  *
@@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo
 } DroppedImmvInfo;
 
 static HTAB *mv_trigger_info = NULL;
+static HTAB *mv_query_cache = NULL;
 static HTAB *dropped_immv = NULL;
 
 static HTAB *LastIvmUpdateHash;
@@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old,
 static void append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 						  StringInfo buf_new, StringInfo aggs_list,
 						  const char *aggtype);
+static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min);
 static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2,
 					 const char* count_col, const char *castType);
 static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
@@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old,
 				List *keys);
 static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname);
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc);
 static void apply_new_delta(const char *matviewname, const char *deltaname_new,
 				StringInfo target_list);
 static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
 				List *keys, StringInfo target_list, StringInfo aggs_set,
 				const char* count_colname);
 static char *get_matching_condition_string(List *keys);
+static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys);
+static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list);
+static char *get_select_for_recalc_string(List *keys);
+static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel);
+static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes);
+static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes);
 static void generate_equal(StringInfo querybuf, Oid opttype,
 			   const char *leftop, const char *rightop);
 
 static void mv_InitHashTables(void);
+static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key);
+static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan);
+static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type);
 static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
 									SubTransactionId subxid);
 static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
@@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	ListCell	*lc;
 	int			i;
 	List	   *keys = NIL;
+	List	   *minmax_list = NIL;
+	List	   *is_min_list = NIL;
 
 
 	/*
@@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 				append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf,
 										  format_type_be(aggref->aggtype));
 
+			/* min/max */
+			else if (!strcmp(aggname, "min") || !strcmp(aggname, "max"))
+			{
+				bool	is_min = (!strcmp(aggname, "min"));
+
+				append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min);
+
+				/* make a resname list of min and max aggregates */
+				minmax_list = lappend(minmax_list, resname);
+				is_min_list = lappend_int(is_min_list, is_min);
+			}
 			else
 				elog(ERROR, "unsupported aggregate function: %s", aggname);
 		}
@@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
 	{
 		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		SPITupleTable  *tuptable_recalc = NULL;
+		uint64			num_recalc;
 		int				rc;
 
 		/* convert tuplestores to ENR, and register for SPI */
@@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 			/* apply old delta and get rows to be recalculated */
 			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
 									   keys, aggs_list_buf, aggs_set_old,
-									   count_colname);
+									   minmax_list, is_min_list,
+									   count_colname, &tuptable_recalc, &num_recalc);
 		else
 			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
 
+		/*
+		 * If we have min or max, we might have to recalculate aggregate values from base tables
+		 * on some tuples. TIDs and keys such tuples are returned as a result of the above query.
+		 */
+		if (minmax_list && tuptable_recalc)
+			recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel);
+
 	}
 	/* For tuple insertion */
 	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
@@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 	);
 }
 
+/*
+ * append_set_clause_for_minmax
+ *
+ * Append SET clause string for min or max aggregation to given buffers.
+ * Also, append resnames required for calculating the aggregate value.
+ * is_min is true if this is min, false if not.
+ */
+static void
+append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min)
+{
+	char *count_col = IVM_colname("count", resname);
+
+	/* For tuple deletion */
+	if (buf_old)
+	{
+		/*
+		 * If the new value doesn't became NULL then use the value remaining
+		 * in the view although this will be recomputated afterwords.
+		 */
+		appendStringInfo(buf_old,
+			", %s = CASE WHEN %s THEN NULL ELSE %s END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_SUB, "mv", "t", count_col),
+			quote_qualified_identifier("mv", resname)
+		);
+		/* count = mv.count - t.count */
+		appendStringInfo(buf_old,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL)
+		);
+	}
+	/* For tuple insertion */
+	if (buf_new)
+	{
+		/*
+		 * min = LEAST(mv.min, diff.min)
+		 * max = GREATEST(mv.max, diff.max)
+		 */
+		appendStringInfo(buf_new,
+			", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_ADD, "mv", "diff", count_col),
+
+			is_min ? "LEAST" : "GREATEST",
+			quote_qualified_identifier("mv", resname),
+			quote_qualified_identifier("diff", resname)
+		);
+		/* count = mv.count + diff.count */
+		appendStringInfo(buf_new,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL)
+		);
+	}
+
+	appendStringInfo(aggs_list, ", %s, %s",
+		quote_qualified_identifier("diff", resname),
+		quote_qualified_identifier("diff", IVM_colname("count", resname))
+	);
+}
+
 /*
  * get_operation_string
  *
@@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
  * list to identify a tuple in the view. If the view has aggregates, this
  * requires strings representing resnames of aggregates and SET clause for
  * updating aggregate values.
+ *
+ * If the view has min or max aggregate, this requires a list of resnames of
+ * min/max aggregates and a list of boolean which represents which entries in
+ * minmax_list is min. These are necessary to check if we need to recalculate
+ * min or max aggregate values. In this case, this query returns TID and keys
+ * of tuples which need to be recalculated.  This result and the number of rows
+ * are stored in tuptables and num_recalc repectedly.
+ *
  */
 static void
 apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname)
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc)
 {
 	StringInfoData	querybuf;
 	char   *match_cond;
+	char   *updt_returning = "";
+	char   *select_for_recalc = "SELECT";
 	bool	agg_without_groupby = (list_length(keys) == 0);
 
+	Assert(tuptable_recalc != NULL);
+	Assert(num_recalc != NULL);
+
 	/* build WHERE condition for searching tuples to be deleted */
 	match_cond = get_matching_condition_string(keys);
 
+	/*
+	 * We need a special RETURNING clause and SELECT statement for min/max to
+	 * check which tuple needs re-calculation from base tables.
+	 */
+	if (minmax_list)
+	{
+		updt_returning = get_returning_string(minmax_list, is_min_list, keys);
+		select_for_recalc = get_select_for_recalc_string(keys);
+	}
+
 	/* Search for matching tuples from the view and update or delete if found. */
 	initStringInfo(&querybuf);
 	appendStringInfo(&querybuf,
@@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
 											"%s"	/* SET clauses for aggregates */
 						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
-					")"
-					/* delete a tuple if this is to be deleted */
-					"DELETE FROM %s AS mv USING t "
-					"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt",
+						"%s"						/* RETURNING clause for recalc infomation */
+					"), dlt AS ("			/* delete a tuple if this is to be deleted */
+						"DELETE FROM %s AS mv USING t "
+						"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt"
+					") %s",							/* SELECT returning which tuples need to be recalculated */
 					count_colname,
 					count_colname, count_colname, (agg_without_groupby ? "false" : "true"),
 					(aggs_list != NULL ? aggs_list->data : ""),
@@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 					match_cond,
 					matviewname, count_colname, count_colname, count_colname,
 					(aggs_set != NULL ? aggs_set->data : ""),
-					matviewname);
+					updt_returning,
+					matviewname,
+					select_for_recalc);
 
-	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT)
 		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+
+
+	/* Return tuples to be recalculated. */
+	if (minmax_list)
+	{
+		*tuptable_recalc = SPI_tuptable;
+		*num_recalc = SPI_processed;
+	}
+	else
+	{
+		*tuptable_recalc = NULL;
+		*num_recalc = 0;
+	}
 }
 
 /*
@@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys)
 	return match_cond.data;
 }
 
+/*
+ * get_returning_string
+ *
+ * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count.
+ * This clause returns ctid and a boolean value that indicates if we need to
+ * recalculate min or max value, for each updated row.
+ */
+static char *
+get_returning_string(List *minmax_list, List *is_min_list, List *keys)
+{
+	StringInfoData returning;
+	char		*recalc_cond;
+	ListCell	*lc;
+
+	Assert(minmax_list != NIL && is_min_list != NIL);
+	recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list);
+
+	initStringInfo(&returning);
+
+	appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char *resname = NameStr(attr->attname);
+		appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname));
+	}
+
+	return returning.data;
+}
+
+/*
+ * get_minmax_recalc_condition_string
+ *
+ * Build a predicate string for checking if any min/max aggregate
+ * value needs to be recalculated.
+ */
+static char *
+get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list)
+{
+	StringInfoData recalc_cond;
+	ListCell	*lc1, *lc2;
+
+	initStringInfo(&recalc_cond);
+
+	Assert (list_length(minmax_list) == list_length(is_min_list));
+
+	forboth (lc1, minmax_list, lc2, is_min_list)
+	{
+		char   *resname = (char *) lfirst(lc1);
+		bool	is_min = (bool) lfirst_int(lc2);
+		char   *op_str = (is_min ? ">=" : "<=");
+
+		appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s",
+			quote_qualified_identifier("mv", resname),
+			op_str,
+			quote_qualified_identifier("t", resname)
+		);
+
+		if (lnext(minmax_list, lc1))
+			appendStringInfo(&recalc_cond, " OR ");
+	}
+
+	return recalc_cond.data;
+}
+
+/*
+ * get_select_for_recalc_string
+ *
+ * Build a query to return tid and keys of tuples which need
+ * recalculation. This is used as the result of the query
+ * built by apply_old_delta.
+ */
+static char *
+get_select_for_recalc_string(List *keys)
+{
+	StringInfoData qry;
+	ListCell	*lc;
+
+	initStringInfo(&qry);
+
+	appendStringInfo(&qry, "SELECT tid");
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		appendStringInfo(&qry, ", %s", NameStr(attr->attname));
+	}
+
+	appendStringInfo(&qry, " FROM updt WHERE recalc");
+
+	return qry.data;
+}
+
+/*
+ * recalc_and_set_values
+ *
+ * Recalculate tuples in a materialized from base tables and update these.
+ * The tuples which needs recalculation are specified by keys, and resnames
+ * of columns to be updated are specified by namelist. TIDs and key values
+ * are given by tuples in tuptable_recalc. Its first attribute must be TID
+ * and key values must be following this.
+ */
+static void
+recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel)
+{
+	TupleDesc   tupdesc_recalc = tuptable_recalc->tupdesc;
+	Oid		   *keyTypes = NULL, *types = NULL;
+	char	   *keyNulls = NULL, *nulls = NULL;
+	Datum	   *keyVals = NULL, *vals = NULL;
+	int			num_vals = list_length(namelist);
+	int			num_keys = list_length(keys);
+	uint64      i;
+	Oid			matviewOid;
+	char	   *matviewname;
+
+	matviewOid = RelationGetRelid(matviewRel);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/* If we have keys, initialize arrays for them. */
+	if (keys)
+	{
+		keyTypes = palloc(sizeof(Oid) * num_keys);
+		keyNulls = palloc(sizeof(char) * num_keys);
+		keyVals = palloc(sizeof(Datum) * num_keys);
+		/* a tuple contains keys to be recalculated and ctid to be updated*/
+		Assert(tupdesc_recalc->natts == num_keys + 1);
+
+		/* Types of key attributes  */
+		for (i = 0; i < num_keys; i++)
+			keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid;
+	}
+
+	/* allocate memory for all attribute names and tid */
+	types = palloc(sizeof(Oid) * (num_vals + 1));
+	nulls = palloc(sizeof(char) * (num_vals + 1));
+	vals = palloc(sizeof(Datum) * (num_vals + 1));
+
+	/* For each tuple which needs recalculation */
+	for (i = 0; i < num_tuples; i++)
+	{
+		int j;
+		bool isnull;
+		SPIPlanPtr plan;
+		SPITupleTable *tuptable_newvals;
+		TupleDesc   tupdesc_newvals;
+
+		/* Set group key values as parameters if needed. */
+		if (keys)
+		{
+			for (j = 0; j < num_keys; j++)
+			{
+				keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull);
+				if (isnull)
+					keyNulls[j] = 'n';
+				else
+					keyNulls[j] = ' ';
+			}
+		}
+
+		/*
+		 * Get recalculated values from base tables. The result must be
+		 * only one tuple thich contains the new values for specified keys.
+		 */
+		plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes);
+		if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT)
+			elog(ERROR, "SPI_execute_plan");
+		if (SPI_processed != 1)
+			elog(ERROR, "SPI_execute_plan returned zero or more than one rows");
+
+		tuptable_newvals = SPI_tuptable;
+		tupdesc_newvals = tuptable_newvals->tupdesc;
+
+		Assert(tupdesc_newvals->natts == num_vals);
+
+		/* Set the new values as parameters */
+		for (j = 0; j < tupdesc_newvals->natts; j++)
+		{
+			if (i == 0)
+				types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid;
+
+			vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull);
+			if (isnull)
+				nulls[j] = 'n';
+			else
+				nulls[j] = ' ';
+		}
+		/* Set TID of the view tuple to be updated as a parameter */
+		types[j] = TIDOID;
+		vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull);
+		nulls[j] = ' ';
+
+		/* Update the view tuple to the new values */
+		plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types);
+		if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE)
+			elog(ERROR, "SPI_execute_plan");
+	}
+}
+
+
+/*
+ * get_plan_for_recalc
+ *
+ * Create or fetch a plan for recalculating value in the view's target list
+ * from base tables using the definition query of materialized view specified
+ * by matviewOid. namelist is a list of resnames of values to be recalculated.
+ *
+ * keys is a list of keys to identify tuples to be recalculated if this is not
+ * empty. KeyTypes is an array of types of keys.
+ */
+static SPIPlanPtr
+get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes)
+{
+	MV_QueryKey hash_key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the recalculation */
+	mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC);
+	if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL)
+	{
+		ListCell	   *lc;
+		StringInfoData	str;
+		char   *viewdef;
+
+		/* get view definition of matview */
+		viewdef = text_to_cstring((text *) DatumGetPointer(
+					DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid))));
+		/* get rid of trailing semi-colon */
+		viewdef[strlen(viewdef)-1] = '\0';
+
+		/*
+		 * Build a query string for recalculating values. This is like
+		 *
+		 *  SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv
+		 *   WHERE (key1, key2, ...) = ($1, $2, ...);
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "SELECT ");
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, " FROM (%s) mv", viewdef);
+
+		if (keys)
+		{
+			int		i = 1;
+			char	paramname[16];
+
+			appendStringInfo(&str, " WHERE (");
+			foreach (lc, keys)
+			{
+				Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+				char   *resname = NameStr(attr->attname);
+				Oid		typid = attr->atttypid;
+
+				sprintf(paramname, "$%d", i);
+				appendStringInfo(&str, "(");
+				generate_equal(&str, typid, resname, paramname);
+				appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))",
+								 resname, paramname);
+
+				if (lnext(keys, lc))
+					appendStringInfoString(&str, " AND ");
+				i++;
+			}
+			appendStringInfo(&str, ")");
+		}
+		else
+			keyTypes = NULL;
+
+		plan = SPI_prepare(str.data, list_length(keys), keyTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&hash_key, plan);
+	}
+
+	return plan;
+}
+
+/*
+ * get_plan_for_set_values
+ *
+ * Create or fetch a plan for applying new values calculated by
+ * get_plan_for_recalc to a materialized view specified by matviewOid.
+ * matviewname is the name of the view.  namelist is a list of resnames
+ * of attributes to be updated, and valTypes is an array of types of the
+ * values.
+ */
+static SPIPlanPtr
+get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes)
+{
+	MV_QueryKey	key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the real check */
+	mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE);
+	if ((plan = mv_FetchPreparedPlan(&key)) == NULL)
+	{
+		ListCell	  *lc;
+		StringInfoData str;
+		int		i;
+
+		/*
+		 * Build a query string for applying min/max values. This is like
+		 *
+		 *  UPDATE matviewname AS mv
+		 *   SET (x1, x2, x3, x4) = ($1, $2, $3, $4)
+		 *   WHERE ctid = $5;
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname);
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, ") = ROW(");
+
+		for (i = 1; i <= list_length(namelist); i++)
+			appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i);
+
+		appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i);
+
+		plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&key, plan);
+	}
+
+	return plan;
+}
+
 /*
  * generate_equals
  *
@@ -3025,6 +3541,13 @@ mv_InitHashTables(void)
 {
 	HASHCTL		ctl;
 
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(MV_QueryKey);
+	ctl.entrysize = sizeof(MV_QueryHashEntry);
+	mv_query_cache = hash_create("MV query cache",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
 	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(MV_TriggerHashEntry);
@@ -3039,6 +3562,109 @@ mv_InitHashTables(void)
 							   &ctl, HASH_ELEM | HASH_BLOBS);
 }
 
+/*
+ * mv_FetchPreparedPlan
+ */
+static SPIPlanPtr
+mv_FetchPreparedPlan(MV_QueryKey *key)
+{
+	MV_QueryHashEntry *entry;
+	SPIPlanPtr	plan;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Lookup for the key
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_FIND, NULL);
+	if (entry == NULL)
+		return NULL;
+
+	/*
+	 * Check whether the plan is still valid.  If it isn't, we don't want to
+	 * simply rely on plancache.c to regenerate it; rather we should start
+	 * from scratch and rebuild the query text too.  This is to cover cases
+	 * such as table/column renames.  We depend on the plancache machinery to
+	 * detect possible invalidations, though.
+	 *
+	 * CAUTION: this check is only trustworthy if the caller has already
+	 * locked both materialized views and base tables.
+	 *
+	 * Also, check whether the search_path is still the same as when we made it.
+	 * If it isn't, we need to rebuild the query text because the result of
+	 * pg_ivm_get_viewdef() will change.
+	 */
+	plan = entry->plan;
+	if (plan && SPI_plan_is_valid(plan) &&
+		SearchPathMatchesCurrentEnvironment(entry->search_path))
+		return plan;
+
+	/*
+	 * Otherwise we might as well flush the cached plan now, to free a little
+	 * memory space before we make a new one.
+	 */
+	if (plan)
+		SPI_freeplan(plan);
+	if (entry->search_path)
+		pfree(entry->search_path);
+
+	entry->plan = NULL;
+	entry->search_path = NULL;
+
+	return NULL;
+}
+
+/*
+ * mv_HashPreparedPlan
+ *
+ * Add another plan to our private SPI query plan hashtable.
+ */
+static void
+mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan)
+{
+	MV_QueryHashEntry *entry;
+	bool		found;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Add the new plan.  We might be overwriting an entry previously found
+	 * invalid by mv_FetchPreparedPlan.
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_ENTER, &found);
+	Assert(!found || entry->plan == NULL);
+	entry->plan = plan;
+	entry->search_path = GetSearchPathMatcher(TopMemoryContext);
+}
+
+/*
+ * mv_BuildQueryKey
+ *
+ * Construct a hashtable key for a prepared SPI plan for IVM.
+ */
+static void
+mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type)
+{
+	/*
+	 * We assume struct MV_QueryKey contains no padding bytes, else we'd need
+	 * to use memset to clear them.
+	 */
+	key->matview_id = matview_id;
+	key->query_type = query_type;
+}
+
 /*
  * AtAbort_IVM
  *
-- 
2.43.0


--Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ
Content-Type: text/x-diff;
 name="v38-0008-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v38-0008-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 259+ messages in thread

* [PATCH v37 09/11] Add support for min/max aggregates for IVM
@ 2023-05-31 11:58  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 259+ messages in thread

From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw)

Supporting min and max is more complicated than count, sum, or avg.

For an example of min, when tuples are inserted, the current min value
in the view and the min value in the inseteted tuples are compared,
then the smaller one is used as the latest min value. On the other
hand, when tuples are deleted, if the current min value in the view
equals to the min in the deleted tuples, we need re-computation the
latest min value from base tables. Otherwise, the current value in
the view remains.
---
 src/backend/commands/createas.c |  45 +++
 src/backend/commands/matview.c  | 644 +++++++++++++++++++++++++++++++-
 2 files changed, 680 insertions(+), 9 deletions(-)

diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 45a30309951..ed67f399b7c 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid)
 		case F_AVG_FLOAT8:
 		case F_AVG_INTERVAL:
 
+		/* min */
+		case F_MIN_ANYARRAY:
+		case F_MIN_INT8:
+		case F_MIN_INT4:
+		case F_MIN_INT2:
+		case F_MIN_OID:
+		case F_MIN_FLOAT4:
+		case F_MIN_FLOAT8:
+		case F_MIN_DATE:
+		case F_MIN_TIME:
+		case F_MIN_TIMETZ:
+		case F_MIN_MONEY:
+		case F_MIN_TIMESTAMP:
+		case F_MIN_TIMESTAMPTZ:
+		case F_MIN_INTERVAL:
+		case F_MIN_TEXT:
+		case F_MIN_NUMERIC:
+		case F_MIN_BPCHAR:
+		case F_MIN_TID:
+		case F_MIN_ANYENUM:
+		case F_MIN_INET:
+		case F_MIN_PG_LSN:
+
+		/* max */
+		case F_MAX_ANYARRAY:
+		case F_MAX_INT8:
+		case F_MAX_INT4:
+		case F_MAX_INT2:
+		case F_MAX_OID:
+		case F_MAX_FLOAT4:
+		case F_MAX_FLOAT8:
+		case F_MAX_DATE:
+		case F_MAX_TIME:
+		case F_MAX_TIMETZ:
+		case F_MAX_MONEY:
+		case F_MAX_TIMESTAMP:
+		case F_MAX_TIMESTAMPTZ:
+		case F_MAX_INTERVAL:
+		case F_MAX_TEXT:
+		case F_MAX_NUMERIC:
+		case F_MAX_BPCHAR:
+		case F_MAX_TID:
+		case F_MAX_ANYENUM:
+		case F_MAX_INET:
+		case F_MAX_PG_LSN:
 			return true;
 
 		default:
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 710224aa994..3b3871c49e2 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -69,6 +69,34 @@ typedef struct
 
 #define MV_INIT_QUERYHASHSIZE	16
 
+/* MV query type codes */
+#define MV_PLAN_RECALC			1
+#define MV_PLAN_SET_VALUE		2
+
+/*
+ * MI_QueryKey
+ *
+ * The key identifying a prepared SPI plan in our query hashtable
+ */
+typedef struct MV_QueryKey
+{
+	Oid			matview_id;	/* OID of materialized view */
+	int32		query_type;	/* query type ID, see MV_PLAN_XXX above */
+} MV_QueryKey;
+
+/*
+ * MV_QueryHashEntry
+ *
+ * Hash entry for cached plans used to maintain materialized views.
+ */
+typedef struct MV_QueryHashEntry
+{
+	MV_QueryKey key;
+	SPIPlanPtr	plan;
+	SearchPathMatcher *search_path;        /* search_path used for parsing
+											 * and planning */
+} MV_QueryHashEntry;
+
 /*
  * MV_TriggerHashEntry
  *
@@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo
 } DroppedImmvInfo;
 
 static HTAB *mv_trigger_info = NULL;
+static HTAB *mv_query_cache = NULL;
 static HTAB *dropped_immv = NULL;
 
 static HTAB *LastIvmUpdateHash;
@@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old,
 static void append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 						  StringInfo buf_new, StringInfo aggs_list,
 						  const char *aggtype);
+static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min);
 static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2,
 					 const char* count_col, const char *castType);
 static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
@@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old,
 				List *keys);
 static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname);
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc);
 static void apply_new_delta(const char *matviewname, const char *deltaname_new,
 				StringInfo target_list);
 static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
 				List *keys, StringInfo target_list, StringInfo aggs_set,
 				const char* count_colname);
 static char *get_matching_condition_string(List *keys);
+static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys);
+static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list);
+static char *get_select_for_recalc_string(List *keys);
+static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel);
+static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes);
+static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes);
 static void generate_equal(StringInfo querybuf, Oid opttype,
 			   const char *leftop, const char *rightop);
 
 static void mv_InitHashTables(void);
+static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key);
+static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan);
+static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type);
 static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
 									SubTransactionId subxid);
 static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
@@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	ListCell	*lc;
 	int			i;
 	List	   *keys = NIL;
+	List	   *minmax_list = NIL;
+	List	   *is_min_list = NIL;
 
 
 	/*
@@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 				append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf,
 										  format_type_be(aggref->aggtype));
 
+			/* min/max */
+			else if (!strcmp(aggname, "min") || !strcmp(aggname, "max"))
+			{
+				bool	is_min = (!strcmp(aggname, "min"));
+
+				append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min);
+
+				/* make a resname list of min and max aggregates */
+				minmax_list = lappend(minmax_list, resname);
+				is_min_list = lappend_int(is_min_list, is_min);
+			}
 			else
 				elog(ERROR, "unsupported aggregate function: %s", aggname);
 		}
@@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
 	{
 		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		SPITupleTable  *tuptable_recalc = NULL;
+		uint64			num_recalc;
 		int				rc;
 
 		/* convert tuplestores to ENR, and register for SPI */
@@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 			/* apply old delta and get rows to be recalculated */
 			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
 									   keys, aggs_list_buf, aggs_set_old,
-									   count_colname);
+									   minmax_list, is_min_list,
+									   count_colname, &tuptable_recalc, &num_recalc);
 		else
 			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
 
+		/*
+		 * If we have min or max, we might have to recalculate aggregate values from base tables
+		 * on some tuples. TIDs and keys such tuples are returned as a result of the above query.
+		 */
+		if (minmax_list && tuptable_recalc)
+			recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel);
+
 	}
 	/* For tuple insertion */
 	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
@@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 	);
 }
 
+/*
+ * append_set_clause_for_minmax
+ *
+ * Append SET clause string for min or max aggregation to given buffers.
+ * Also, append resnames required for calculating the aggregate value.
+ * is_min is true if this is min, false if not.
+ */
+static void
+append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min)
+{
+	char *count_col = IVM_colname("count", resname);
+
+	/* For tuple deletion */
+	if (buf_old)
+	{
+		/*
+		 * If the new value doesn't became NULL then use the value remaining
+		 * in the view although this will be recomputated afterwords.
+		 */
+		appendStringInfo(buf_old,
+			", %s = CASE WHEN %s THEN NULL ELSE %s END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_SUB, "mv", "t", count_col),
+			quote_qualified_identifier("mv", resname)
+		);
+		/* count = mv.count - t.count */
+		appendStringInfo(buf_old,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL)
+		);
+	}
+	/* For tuple insertion */
+	if (buf_new)
+	{
+		/*
+		 * min = LEAST(mv.min, diff.min)
+		 * max = GREATEST(mv.max, diff.max)
+		 */
+		appendStringInfo(buf_new,
+			", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_ADD, "mv", "diff", count_col),
+
+			is_min ? "LEAST" : "GREATEST",
+			quote_qualified_identifier("mv", resname),
+			quote_qualified_identifier("diff", resname)
+		);
+		/* count = mv.count + diff.count */
+		appendStringInfo(buf_new,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL)
+		);
+	}
+
+	appendStringInfo(aggs_list, ", %s, %s",
+		quote_qualified_identifier("diff", resname),
+		quote_qualified_identifier("diff", IVM_colname("count", resname))
+	);
+}
+
 /*
  * get_operation_string
  *
@@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
  * list to identify a tuple in the view. If the view has aggregates, this
  * requires strings representing resnames of aggregates and SET clause for
  * updating aggregate values.
+ *
+ * If the view has min or max aggregate, this requires a list of resnames of
+ * min/max aggregates and a list of boolean which represents which entries in
+ * minmax_list is min. These are necessary to check if we need to recalculate
+ * min or max aggregate values. In this case, this query returns TID and keys
+ * of tuples which need to be recalculated.  This result and the number of rows
+ * are stored in tuptables and num_recalc repectedly.
+ *
  */
 static void
 apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname)
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc)
 {
 	StringInfoData	querybuf;
 	char   *match_cond;
+	char   *updt_returning = "";
+	char   *select_for_recalc = "SELECT";
 	bool	agg_without_groupby = (list_length(keys) == 0);
 
+	Assert(tuptable_recalc != NULL);
+	Assert(num_recalc != NULL);
+
 	/* build WHERE condition for searching tuples to be deleted */
 	match_cond = get_matching_condition_string(keys);
 
+	/*
+	 * We need a special RETURNING clause and SELECT statement for min/max to
+	 * check which tuple needs re-calculation from base tables.
+	 */
+	if (minmax_list)
+	{
+		updt_returning = get_returning_string(minmax_list, is_min_list, keys);
+		select_for_recalc = get_select_for_recalc_string(keys);
+	}
+
 	/* Search for matching tuples from the view and update or delete if found. */
 	initStringInfo(&querybuf);
 	appendStringInfo(&querybuf,
@@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
 											"%s"	/* SET clauses for aggregates */
 						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
-					")"
-					/* delete a tuple if this is to be deleted */
-					"DELETE FROM %s AS mv USING t "
-					"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt",
+						"%s"						/* RETURNING clause for recalc infomation */
+					"), dlt AS ("			/* delete a tuple if this is to be deleted */
+						"DELETE FROM %s AS mv USING t "
+						"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt"
+					") %s",							/* SELECT returning which tuples need to be recalculated */
 					count_colname,
 					count_colname, count_colname, (agg_without_groupby ? "false" : "true"),
 					(aggs_list != NULL ? aggs_list->data : ""),
@@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 					match_cond,
 					matviewname, count_colname, count_colname, count_colname,
 					(aggs_set != NULL ? aggs_set->data : ""),
-					matviewname);
+					updt_returning,
+					matviewname,
+					select_for_recalc);
 
-	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT)
 		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+
+
+	/* Return tuples to be recalculated. */
+	if (minmax_list)
+	{
+		*tuptable_recalc = SPI_tuptable;
+		*num_recalc = SPI_processed;
+	}
+	else
+	{
+		*tuptable_recalc = NULL;
+		*num_recalc = 0;
+	}
 }
 
 /*
@@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys)
 	return match_cond.data;
 }
 
+/*
+ * get_returning_string
+ *
+ * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count.
+ * This clause returns ctid and a boolean value that indicates if we need to
+ * recalculate min or max value, for each updated row.
+ */
+static char *
+get_returning_string(List *minmax_list, List *is_min_list, List *keys)
+{
+	StringInfoData returning;
+	char		*recalc_cond;
+	ListCell	*lc;
+
+	Assert(minmax_list != NIL && is_min_list != NIL);
+	recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list);
+
+	initStringInfo(&returning);
+
+	appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char *resname = NameStr(attr->attname);
+		appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname));
+	}
+
+	return returning.data;
+}
+
+/*
+ * get_minmax_recalc_condition_string
+ *
+ * Build a predicate string for checking if any min/max aggregate
+ * value needs to be recalculated.
+ */
+static char *
+get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list)
+{
+	StringInfoData recalc_cond;
+	ListCell	*lc1, *lc2;
+
+	initStringInfo(&recalc_cond);
+
+	Assert (list_length(minmax_list) == list_length(is_min_list));
+
+	forboth (lc1, minmax_list, lc2, is_min_list)
+	{
+		char   *resname = (char *) lfirst(lc1);
+		bool	is_min = (bool) lfirst_int(lc2);
+		char   *op_str = (is_min ? ">=" : "<=");
+
+		appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s",
+			quote_qualified_identifier("mv", resname),
+			op_str,
+			quote_qualified_identifier("t", resname)
+		);
+
+		if (lnext(minmax_list, lc1))
+			appendStringInfo(&recalc_cond, " OR ");
+	}
+
+	return recalc_cond.data;
+}
+
+/*
+ * get_select_for_recalc_string
+ *
+ * Build a query to return tid and keys of tuples which need
+ * recalculation. This is used as the result of the query
+ * built by apply_old_delta.
+ */
+static char *
+get_select_for_recalc_string(List *keys)
+{
+	StringInfoData qry;
+	ListCell	*lc;
+
+	initStringInfo(&qry);
+
+	appendStringInfo(&qry, "SELECT tid");
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		appendStringInfo(&qry, ", %s", NameStr(attr->attname));
+	}
+
+	appendStringInfo(&qry, " FROM updt WHERE recalc");
+
+	return qry.data;
+}
+
+/*
+ * recalc_and_set_values
+ *
+ * Recalculate tuples in a materialized from base tables and update these.
+ * The tuples which needs recalculation are specified by keys, and resnames
+ * of columns to be updated are specified by namelist. TIDs and key values
+ * are given by tuples in tuptable_recalc. Its first attribute must be TID
+ * and key values must be following this.
+ */
+static void
+recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel)
+{
+	TupleDesc   tupdesc_recalc = tuptable_recalc->tupdesc;
+	Oid		   *keyTypes = NULL, *types = NULL;
+	char	   *keyNulls = NULL, *nulls = NULL;
+	Datum	   *keyVals = NULL, *vals = NULL;
+	int			num_vals = list_length(namelist);
+	int			num_keys = list_length(keys);
+	uint64      i;
+	Oid			matviewOid;
+	char	   *matviewname;
+
+	matviewOid = RelationGetRelid(matviewRel);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/* If we have keys, initialize arrays for them. */
+	if (keys)
+	{
+		keyTypes = palloc(sizeof(Oid) * num_keys);
+		keyNulls = palloc(sizeof(char) * num_keys);
+		keyVals = palloc(sizeof(Datum) * num_keys);
+		/* a tuple contains keys to be recalculated and ctid to be updated*/
+		Assert(tupdesc_recalc->natts == num_keys + 1);
+
+		/* Types of key attributes  */
+		for (i = 0; i < num_keys; i++)
+			keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid;
+	}
+
+	/* allocate memory for all attribute names and tid */
+	types = palloc(sizeof(Oid) * (num_vals + 1));
+	nulls = palloc(sizeof(char) * (num_vals + 1));
+	vals = palloc(sizeof(Datum) * (num_vals + 1));
+
+	/* For each tuple which needs recalculation */
+	for (i = 0; i < num_tuples; i++)
+	{
+		int j;
+		bool isnull;
+		SPIPlanPtr plan;
+		SPITupleTable *tuptable_newvals;
+		TupleDesc   tupdesc_newvals;
+
+		/* Set group key values as parameters if needed. */
+		if (keys)
+		{
+			for (j = 0; j < num_keys; j++)
+			{
+				keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull);
+				if (isnull)
+					keyNulls[j] = 'n';
+				else
+					keyNulls[j] = ' ';
+			}
+		}
+
+		/*
+		 * Get recalculated values from base tables. The result must be
+		 * only one tuple thich contains the new values for specified keys.
+		 */
+		plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes);
+		if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT)
+			elog(ERROR, "SPI_execute_plan");
+		if (SPI_processed != 1)
+			elog(ERROR, "SPI_execute_plan returned zero or more than one rows");
+
+		tuptable_newvals = SPI_tuptable;
+		tupdesc_newvals = tuptable_newvals->tupdesc;
+
+		Assert(tupdesc_newvals->natts == num_vals);
+
+		/* Set the new values as parameters */
+		for (j = 0; j < tupdesc_newvals->natts; j++)
+		{
+			if (i == 0)
+				types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid;
+
+			vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull);
+			if (isnull)
+				nulls[j] = 'n';
+			else
+				nulls[j] = ' ';
+		}
+		/* Set TID of the view tuple to be updated as a parameter */
+		types[j] = TIDOID;
+		vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull);
+		nulls[j] = ' ';
+
+		/* Update the view tuple to the new values */
+		plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types);
+		if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE)
+			elog(ERROR, "SPI_execute_plan");
+	}
+}
+
+
+/*
+ * get_plan_for_recalc
+ *
+ * Create or fetch a plan for recalculating value in the view's target list
+ * from base tables using the definition query of materialized view specified
+ * by matviewOid. namelist is a list of resnames of values to be recalculated.
+ *
+ * keys is a list of keys to identify tuples to be recalculated if this is not
+ * empty. KeyTypes is an array of types of keys.
+ */
+static SPIPlanPtr
+get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes)
+{
+	MV_QueryKey hash_key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the recalculation */
+	mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC);
+	if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL)
+	{
+		ListCell	   *lc;
+		StringInfoData	str;
+		char   *viewdef;
+
+		/* get view definition of matview */
+		viewdef = text_to_cstring((text *) DatumGetPointer(
+					DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid))));
+		/* get rid of trailing semi-colon */
+		viewdef[strlen(viewdef)-1] = '\0';
+
+		/*
+		 * Build a query string for recalculating values. This is like
+		 *
+		 *  SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv
+		 *   WHERE (key1, key2, ...) = ($1, $2, ...);
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "SELECT ");
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, " FROM (%s) mv", viewdef);
+
+		if (keys)
+		{
+			int		i = 1;
+			char	paramname[16];
+
+			appendStringInfo(&str, " WHERE (");
+			foreach (lc, keys)
+			{
+				Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+				char   *resname = NameStr(attr->attname);
+				Oid		typid = attr->atttypid;
+
+				sprintf(paramname, "$%d", i);
+				appendStringInfo(&str, "(");
+				generate_equal(&str, typid, resname, paramname);
+				appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))",
+								 resname, paramname);
+
+				if (lnext(keys, lc))
+					appendStringInfoString(&str, " AND ");
+				i++;
+			}
+			appendStringInfo(&str, ")");
+		}
+		else
+			keyTypes = NULL;
+
+		plan = SPI_prepare(str.data, list_length(keys), keyTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&hash_key, plan);
+	}
+
+	return plan;
+}
+
+/*
+ * get_plan_for_set_values
+ *
+ * Create or fetch a plan for applying new values calculated by
+ * get_plan_for_recalc to a materialized view specified by matviewOid.
+ * matviewname is the name of the view.  namelist is a list of resnames
+ * of attributes to be updated, and valTypes is an array of types of the
+ * values.
+ */
+static SPIPlanPtr
+get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes)
+{
+	MV_QueryKey	key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the real check */
+	mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE);
+	if ((plan = mv_FetchPreparedPlan(&key)) == NULL)
+	{
+		ListCell	  *lc;
+		StringInfoData str;
+		int		i;
+
+		/*
+		 * Build a query string for applying min/max values. This is like
+		 *
+		 *  UPDATE matviewname AS mv
+		 *   SET (x1, x2, x3, x4) = ($1, $2, $3, $4)
+		 *   WHERE ctid = $5;
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname);
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, ") = ROW(");
+
+		for (i = 1; i <= list_length(namelist); i++)
+			appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i);
+
+		appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i);
+
+		plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&key, plan);
+	}
+
+	return plan;
+}
+
 /*
  * generate_equals
  *
@@ -3025,6 +3541,13 @@ mv_InitHashTables(void)
 {
 	HASHCTL		ctl;
 
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(MV_QueryKey);
+	ctl.entrysize = sizeof(MV_QueryHashEntry);
+	mv_query_cache = hash_create("MV query cache",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
 	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(MV_TriggerHashEntry);
@@ -3039,6 +3562,109 @@ mv_InitHashTables(void)
 							   &ctl, HASH_ELEM | HASH_BLOBS);
 }
 
+/*
+ * mv_FetchPreparedPlan
+ */
+static SPIPlanPtr
+mv_FetchPreparedPlan(MV_QueryKey *key)
+{
+	MV_QueryHashEntry *entry;
+	SPIPlanPtr	plan;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Lookup for the key
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_FIND, NULL);
+	if (entry == NULL)
+		return NULL;
+
+	/*
+	 * Check whether the plan is still valid.  If it isn't, we don't want to
+	 * simply rely on plancache.c to regenerate it; rather we should start
+	 * from scratch and rebuild the query text too.  This is to cover cases
+	 * such as table/column renames.  We depend on the plancache machinery to
+	 * detect possible invalidations, though.
+	 *
+	 * CAUTION: this check is only trustworthy if the caller has already
+	 * locked both materialized views and base tables.
+	 *
+	 * Also, check whether the search_path is still the same as when we made it.
+	 * If it isn't, we need to rebuild the query text because the result of
+	 * pg_ivm_get_viewdef() will change.
+	 */
+	plan = entry->plan;
+	if (plan && SPI_plan_is_valid(plan) &&
+		SearchPathMatchesCurrentEnvironment(entry->search_path))
+		return plan;
+
+	/*
+	 * Otherwise we might as well flush the cached plan now, to free a little
+	 * memory space before we make a new one.
+	 */
+	if (plan)
+		SPI_freeplan(plan);
+	if (entry->search_path)
+		pfree(entry->search_path);
+
+	entry->plan = NULL;
+	entry->search_path = NULL;
+
+	return NULL;
+}
+
+/*
+ * mv_HashPreparedPlan
+ *
+ * Add another plan to our private SPI query plan hashtable.
+ */
+static void
+mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan)
+{
+	MV_QueryHashEntry *entry;
+	bool		found;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Add the new plan.  We might be overwriting an entry previously found
+	 * invalid by mv_FetchPreparedPlan.
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_ENTER, &found);
+	Assert(!found || entry->plan == NULL);
+	entry->plan = plan;
+	entry->search_path = GetSearchPathMatcher(TopMemoryContext);
+}
+
+/*
+ * mv_BuildQueryKey
+ *
+ * Construct a hashtable key for a prepared SPI plan for IVM.
+ */
+static void
+mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type)
+{
+	/*
+	 * We assume struct MV_QueryKey contains no padding bytes, else we'd need
+	 * to use memset to clear them.
+	 */
+	key->matview_id = matview_id;
+	key->query_type = query_type;
+}
+
 /*
  * AtAbort_IVM
  *
-- 
2.43.0


--Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd
Content-Type: text/x-diff;
 name="v37-0008-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v37-0008-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 259+ messages in thread

* [PATCH v38 09/11] Add support for min/max aggregates for IVM
@ 2023-05-31 11:58  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 259+ messages in thread

From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw)

Supporting min and max is more complicated than count, sum, or avg.

For an example of min, when tuples are inserted, the current min value
in the view and the min value in the inseteted tuples are compared,
then the smaller one is used as the latest min value. On the other
hand, when tuples are deleted, if the current min value in the view
equals to the min in the deleted tuples, we need re-computation the
latest min value from base tables. Otherwise, the current value in
the view remains.
---
 src/backend/commands/createas.c |  45 +++
 src/backend/commands/matview.c  | 644 +++++++++++++++++++++++++++++++-
 2 files changed, 680 insertions(+), 9 deletions(-)

diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 35e124694ab..540d9e3d5c8 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid)
 		case F_AVG_FLOAT8:
 		case F_AVG_INTERVAL:
 
+		/* min */
+		case F_MIN_ANYARRAY:
+		case F_MIN_INT8:
+		case F_MIN_INT4:
+		case F_MIN_INT2:
+		case F_MIN_OID:
+		case F_MIN_FLOAT4:
+		case F_MIN_FLOAT8:
+		case F_MIN_DATE:
+		case F_MIN_TIME:
+		case F_MIN_TIMETZ:
+		case F_MIN_MONEY:
+		case F_MIN_TIMESTAMP:
+		case F_MIN_TIMESTAMPTZ:
+		case F_MIN_INTERVAL:
+		case F_MIN_TEXT:
+		case F_MIN_NUMERIC:
+		case F_MIN_BPCHAR:
+		case F_MIN_TID:
+		case F_MIN_ANYENUM:
+		case F_MIN_INET:
+		case F_MIN_PG_LSN:
+
+		/* max */
+		case F_MAX_ANYARRAY:
+		case F_MAX_INT8:
+		case F_MAX_INT4:
+		case F_MAX_INT2:
+		case F_MAX_OID:
+		case F_MAX_FLOAT4:
+		case F_MAX_FLOAT8:
+		case F_MAX_DATE:
+		case F_MAX_TIME:
+		case F_MAX_TIMETZ:
+		case F_MAX_MONEY:
+		case F_MAX_TIMESTAMP:
+		case F_MAX_TIMESTAMPTZ:
+		case F_MAX_INTERVAL:
+		case F_MAX_TEXT:
+		case F_MAX_NUMERIC:
+		case F_MAX_BPCHAR:
+		case F_MAX_TID:
+		case F_MAX_ANYENUM:
+		case F_MAX_INET:
+		case F_MAX_PG_LSN:
 			return true;
 
 		default:
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 710224aa994..3b3871c49e2 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -69,6 +69,34 @@ typedef struct
 
 #define MV_INIT_QUERYHASHSIZE	16
 
+/* MV query type codes */
+#define MV_PLAN_RECALC			1
+#define MV_PLAN_SET_VALUE		2
+
+/*
+ * MI_QueryKey
+ *
+ * The key identifying a prepared SPI plan in our query hashtable
+ */
+typedef struct MV_QueryKey
+{
+	Oid			matview_id;	/* OID of materialized view */
+	int32		query_type;	/* query type ID, see MV_PLAN_XXX above */
+} MV_QueryKey;
+
+/*
+ * MV_QueryHashEntry
+ *
+ * Hash entry for cached plans used to maintain materialized views.
+ */
+typedef struct MV_QueryHashEntry
+{
+	MV_QueryKey key;
+	SPIPlanPtr	plan;
+	SearchPathMatcher *search_path;        /* search_path used for parsing
+											 * and planning */
+} MV_QueryHashEntry;
+
 /*
  * MV_TriggerHashEntry
  *
@@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo
 } DroppedImmvInfo;
 
 static HTAB *mv_trigger_info = NULL;
+static HTAB *mv_query_cache = NULL;
 static HTAB *dropped_immv = NULL;
 
 static HTAB *LastIvmUpdateHash;
@@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old,
 static void append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 						  StringInfo buf_new, StringInfo aggs_list,
 						  const char *aggtype);
+static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min);
 static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2,
 					 const char* count_col, const char *castType);
 static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
@@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old,
 				List *keys);
 static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname);
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc);
 static void apply_new_delta(const char *matviewname, const char *deltaname_new,
 				StringInfo target_list);
 static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
 				List *keys, StringInfo target_list, StringInfo aggs_set,
 				const char* count_colname);
 static char *get_matching_condition_string(List *keys);
+static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys);
+static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list);
+static char *get_select_for_recalc_string(List *keys);
+static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel);
+static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes);
+static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes);
 static void generate_equal(StringInfo querybuf, Oid opttype,
 			   const char *leftop, const char *rightop);
 
 static void mv_InitHashTables(void);
+static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key);
+static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan);
+static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type);
 static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
 									SubTransactionId subxid);
 static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
@@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	ListCell	*lc;
 	int			i;
 	List	   *keys = NIL;
+	List	   *minmax_list = NIL;
+	List	   *is_min_list = NIL;
 
 
 	/*
@@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 				append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf,
 										  format_type_be(aggref->aggtype));
 
+			/* min/max */
+			else if (!strcmp(aggname, "min") || !strcmp(aggname, "max"))
+			{
+				bool	is_min = (!strcmp(aggname, "min"));
+
+				append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min);
+
+				/* make a resname list of min and max aggregates */
+				minmax_list = lappend(minmax_list, resname);
+				is_min_list = lappend_int(is_min_list, is_min);
+			}
 			else
 				elog(ERROR, "unsupported aggregate function: %s", aggname);
 		}
@@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
 	{
 		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		SPITupleTable  *tuptable_recalc = NULL;
+		uint64			num_recalc;
 		int				rc;
 
 		/* convert tuplestores to ENR, and register for SPI */
@@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 			/* apply old delta and get rows to be recalculated */
 			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
 									   keys, aggs_list_buf, aggs_set_old,
-									   count_colname);
+									   minmax_list, is_min_list,
+									   count_colname, &tuptable_recalc, &num_recalc);
 		else
 			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
 
+		/*
+		 * If we have min or max, we might have to recalculate aggregate values from base tables
+		 * on some tuples. TIDs and keys such tuples are returned as a result of the above query.
+		 */
+		if (minmax_list && tuptable_recalc)
+			recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel);
+
 	}
 	/* For tuple insertion */
 	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
@@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 	);
 }
 
+/*
+ * append_set_clause_for_minmax
+ *
+ * Append SET clause string for min or max aggregation to given buffers.
+ * Also, append resnames required for calculating the aggregate value.
+ * is_min is true if this is min, false if not.
+ */
+static void
+append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min)
+{
+	char *count_col = IVM_colname("count", resname);
+
+	/* For tuple deletion */
+	if (buf_old)
+	{
+		/*
+		 * If the new value doesn't became NULL then use the value remaining
+		 * in the view although this will be recomputated afterwords.
+		 */
+		appendStringInfo(buf_old,
+			", %s = CASE WHEN %s THEN NULL ELSE %s END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_SUB, "mv", "t", count_col),
+			quote_qualified_identifier("mv", resname)
+		);
+		/* count = mv.count - t.count */
+		appendStringInfo(buf_old,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL)
+		);
+	}
+	/* For tuple insertion */
+	if (buf_new)
+	{
+		/*
+		 * min = LEAST(mv.min, diff.min)
+		 * max = GREATEST(mv.max, diff.max)
+		 */
+		appendStringInfo(buf_new,
+			", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_ADD, "mv", "diff", count_col),
+
+			is_min ? "LEAST" : "GREATEST",
+			quote_qualified_identifier("mv", resname),
+			quote_qualified_identifier("diff", resname)
+		);
+		/* count = mv.count + diff.count */
+		appendStringInfo(buf_new,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL)
+		);
+	}
+
+	appendStringInfo(aggs_list, ", %s, %s",
+		quote_qualified_identifier("diff", resname),
+		quote_qualified_identifier("diff", IVM_colname("count", resname))
+	);
+}
+
 /*
  * get_operation_string
  *
@@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
  * list to identify a tuple in the view. If the view has aggregates, this
  * requires strings representing resnames of aggregates and SET clause for
  * updating aggregate values.
+ *
+ * If the view has min or max aggregate, this requires a list of resnames of
+ * min/max aggregates and a list of boolean which represents which entries in
+ * minmax_list is min. These are necessary to check if we need to recalculate
+ * min or max aggregate values. In this case, this query returns TID and keys
+ * of tuples which need to be recalculated.  This result and the number of rows
+ * are stored in tuptables and num_recalc repectedly.
+ *
  */
 static void
 apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname)
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc)
 {
 	StringInfoData	querybuf;
 	char   *match_cond;
+	char   *updt_returning = "";
+	char   *select_for_recalc = "SELECT";
 	bool	agg_without_groupby = (list_length(keys) == 0);
 
+	Assert(tuptable_recalc != NULL);
+	Assert(num_recalc != NULL);
+
 	/* build WHERE condition for searching tuples to be deleted */
 	match_cond = get_matching_condition_string(keys);
 
+	/*
+	 * We need a special RETURNING clause and SELECT statement for min/max to
+	 * check which tuple needs re-calculation from base tables.
+	 */
+	if (minmax_list)
+	{
+		updt_returning = get_returning_string(minmax_list, is_min_list, keys);
+		select_for_recalc = get_select_for_recalc_string(keys);
+	}
+
 	/* Search for matching tuples from the view and update or delete if found. */
 	initStringInfo(&querybuf);
 	appendStringInfo(&querybuf,
@@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
 											"%s"	/* SET clauses for aggregates */
 						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
-					")"
-					/* delete a tuple if this is to be deleted */
-					"DELETE FROM %s AS mv USING t "
-					"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt",
+						"%s"						/* RETURNING clause for recalc infomation */
+					"), dlt AS ("			/* delete a tuple if this is to be deleted */
+						"DELETE FROM %s AS mv USING t "
+						"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt"
+					") %s",							/* SELECT returning which tuples need to be recalculated */
 					count_colname,
 					count_colname, count_colname, (agg_without_groupby ? "false" : "true"),
 					(aggs_list != NULL ? aggs_list->data : ""),
@@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 					match_cond,
 					matviewname, count_colname, count_colname, count_colname,
 					(aggs_set != NULL ? aggs_set->data : ""),
-					matviewname);
+					updt_returning,
+					matviewname,
+					select_for_recalc);
 
-	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT)
 		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+
+
+	/* Return tuples to be recalculated. */
+	if (minmax_list)
+	{
+		*tuptable_recalc = SPI_tuptable;
+		*num_recalc = SPI_processed;
+	}
+	else
+	{
+		*tuptable_recalc = NULL;
+		*num_recalc = 0;
+	}
 }
 
 /*
@@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys)
 	return match_cond.data;
 }
 
+/*
+ * get_returning_string
+ *
+ * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count.
+ * This clause returns ctid and a boolean value that indicates if we need to
+ * recalculate min or max value, for each updated row.
+ */
+static char *
+get_returning_string(List *minmax_list, List *is_min_list, List *keys)
+{
+	StringInfoData returning;
+	char		*recalc_cond;
+	ListCell	*lc;
+
+	Assert(minmax_list != NIL && is_min_list != NIL);
+	recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list);
+
+	initStringInfo(&returning);
+
+	appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char *resname = NameStr(attr->attname);
+		appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname));
+	}
+
+	return returning.data;
+}
+
+/*
+ * get_minmax_recalc_condition_string
+ *
+ * Build a predicate string for checking if any min/max aggregate
+ * value needs to be recalculated.
+ */
+static char *
+get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list)
+{
+	StringInfoData recalc_cond;
+	ListCell	*lc1, *lc2;
+
+	initStringInfo(&recalc_cond);
+
+	Assert (list_length(minmax_list) == list_length(is_min_list));
+
+	forboth (lc1, minmax_list, lc2, is_min_list)
+	{
+		char   *resname = (char *) lfirst(lc1);
+		bool	is_min = (bool) lfirst_int(lc2);
+		char   *op_str = (is_min ? ">=" : "<=");
+
+		appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s",
+			quote_qualified_identifier("mv", resname),
+			op_str,
+			quote_qualified_identifier("t", resname)
+		);
+
+		if (lnext(minmax_list, lc1))
+			appendStringInfo(&recalc_cond, " OR ");
+	}
+
+	return recalc_cond.data;
+}
+
+/*
+ * get_select_for_recalc_string
+ *
+ * Build a query to return tid and keys of tuples which need
+ * recalculation. This is used as the result of the query
+ * built by apply_old_delta.
+ */
+static char *
+get_select_for_recalc_string(List *keys)
+{
+	StringInfoData qry;
+	ListCell	*lc;
+
+	initStringInfo(&qry);
+
+	appendStringInfo(&qry, "SELECT tid");
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		appendStringInfo(&qry, ", %s", NameStr(attr->attname));
+	}
+
+	appendStringInfo(&qry, " FROM updt WHERE recalc");
+
+	return qry.data;
+}
+
+/*
+ * recalc_and_set_values
+ *
+ * Recalculate tuples in a materialized from base tables and update these.
+ * The tuples which needs recalculation are specified by keys, and resnames
+ * of columns to be updated are specified by namelist. TIDs and key values
+ * are given by tuples in tuptable_recalc. Its first attribute must be TID
+ * and key values must be following this.
+ */
+static void
+recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel)
+{
+	TupleDesc   tupdesc_recalc = tuptable_recalc->tupdesc;
+	Oid		   *keyTypes = NULL, *types = NULL;
+	char	   *keyNulls = NULL, *nulls = NULL;
+	Datum	   *keyVals = NULL, *vals = NULL;
+	int			num_vals = list_length(namelist);
+	int			num_keys = list_length(keys);
+	uint64      i;
+	Oid			matviewOid;
+	char	   *matviewname;
+
+	matviewOid = RelationGetRelid(matviewRel);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/* If we have keys, initialize arrays for them. */
+	if (keys)
+	{
+		keyTypes = palloc(sizeof(Oid) * num_keys);
+		keyNulls = palloc(sizeof(char) * num_keys);
+		keyVals = palloc(sizeof(Datum) * num_keys);
+		/* a tuple contains keys to be recalculated and ctid to be updated*/
+		Assert(tupdesc_recalc->natts == num_keys + 1);
+
+		/* Types of key attributes  */
+		for (i = 0; i < num_keys; i++)
+			keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid;
+	}
+
+	/* allocate memory for all attribute names and tid */
+	types = palloc(sizeof(Oid) * (num_vals + 1));
+	nulls = palloc(sizeof(char) * (num_vals + 1));
+	vals = palloc(sizeof(Datum) * (num_vals + 1));
+
+	/* For each tuple which needs recalculation */
+	for (i = 0; i < num_tuples; i++)
+	{
+		int j;
+		bool isnull;
+		SPIPlanPtr plan;
+		SPITupleTable *tuptable_newvals;
+		TupleDesc   tupdesc_newvals;
+
+		/* Set group key values as parameters if needed. */
+		if (keys)
+		{
+			for (j = 0; j < num_keys; j++)
+			{
+				keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull);
+				if (isnull)
+					keyNulls[j] = 'n';
+				else
+					keyNulls[j] = ' ';
+			}
+		}
+
+		/*
+		 * Get recalculated values from base tables. The result must be
+		 * only one tuple thich contains the new values for specified keys.
+		 */
+		plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes);
+		if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT)
+			elog(ERROR, "SPI_execute_plan");
+		if (SPI_processed != 1)
+			elog(ERROR, "SPI_execute_plan returned zero or more than one rows");
+
+		tuptable_newvals = SPI_tuptable;
+		tupdesc_newvals = tuptable_newvals->tupdesc;
+
+		Assert(tupdesc_newvals->natts == num_vals);
+
+		/* Set the new values as parameters */
+		for (j = 0; j < tupdesc_newvals->natts; j++)
+		{
+			if (i == 0)
+				types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid;
+
+			vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull);
+			if (isnull)
+				nulls[j] = 'n';
+			else
+				nulls[j] = ' ';
+		}
+		/* Set TID of the view tuple to be updated as a parameter */
+		types[j] = TIDOID;
+		vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull);
+		nulls[j] = ' ';
+
+		/* Update the view tuple to the new values */
+		plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types);
+		if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE)
+			elog(ERROR, "SPI_execute_plan");
+	}
+}
+
+
+/*
+ * get_plan_for_recalc
+ *
+ * Create or fetch a plan for recalculating value in the view's target list
+ * from base tables using the definition query of materialized view specified
+ * by matviewOid. namelist is a list of resnames of values to be recalculated.
+ *
+ * keys is a list of keys to identify tuples to be recalculated if this is not
+ * empty. KeyTypes is an array of types of keys.
+ */
+static SPIPlanPtr
+get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes)
+{
+	MV_QueryKey hash_key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the recalculation */
+	mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC);
+	if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL)
+	{
+		ListCell	   *lc;
+		StringInfoData	str;
+		char   *viewdef;
+
+		/* get view definition of matview */
+		viewdef = text_to_cstring((text *) DatumGetPointer(
+					DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid))));
+		/* get rid of trailing semi-colon */
+		viewdef[strlen(viewdef)-1] = '\0';
+
+		/*
+		 * Build a query string for recalculating values. This is like
+		 *
+		 *  SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv
+		 *   WHERE (key1, key2, ...) = ($1, $2, ...);
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "SELECT ");
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, " FROM (%s) mv", viewdef);
+
+		if (keys)
+		{
+			int		i = 1;
+			char	paramname[16];
+
+			appendStringInfo(&str, " WHERE (");
+			foreach (lc, keys)
+			{
+				Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+				char   *resname = NameStr(attr->attname);
+				Oid		typid = attr->atttypid;
+
+				sprintf(paramname, "$%d", i);
+				appendStringInfo(&str, "(");
+				generate_equal(&str, typid, resname, paramname);
+				appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))",
+								 resname, paramname);
+
+				if (lnext(keys, lc))
+					appendStringInfoString(&str, " AND ");
+				i++;
+			}
+			appendStringInfo(&str, ")");
+		}
+		else
+			keyTypes = NULL;
+
+		plan = SPI_prepare(str.data, list_length(keys), keyTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&hash_key, plan);
+	}
+
+	return plan;
+}
+
+/*
+ * get_plan_for_set_values
+ *
+ * Create or fetch a plan for applying new values calculated by
+ * get_plan_for_recalc to a materialized view specified by matviewOid.
+ * matviewname is the name of the view.  namelist is a list of resnames
+ * of attributes to be updated, and valTypes is an array of types of the
+ * values.
+ */
+static SPIPlanPtr
+get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes)
+{
+	MV_QueryKey	key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the real check */
+	mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE);
+	if ((plan = mv_FetchPreparedPlan(&key)) == NULL)
+	{
+		ListCell	  *lc;
+		StringInfoData str;
+		int		i;
+
+		/*
+		 * Build a query string for applying min/max values. This is like
+		 *
+		 *  UPDATE matviewname AS mv
+		 *   SET (x1, x2, x3, x4) = ($1, $2, $3, $4)
+		 *   WHERE ctid = $5;
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname);
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, ") = ROW(");
+
+		for (i = 1; i <= list_length(namelist); i++)
+			appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i);
+
+		appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i);
+
+		plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&key, plan);
+	}
+
+	return plan;
+}
+
 /*
  * generate_equals
  *
@@ -3025,6 +3541,13 @@ mv_InitHashTables(void)
 {
 	HASHCTL		ctl;
 
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(MV_QueryKey);
+	ctl.entrysize = sizeof(MV_QueryHashEntry);
+	mv_query_cache = hash_create("MV query cache",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
 	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(MV_TriggerHashEntry);
@@ -3039,6 +3562,109 @@ mv_InitHashTables(void)
 							   &ctl, HASH_ELEM | HASH_BLOBS);
 }
 
+/*
+ * mv_FetchPreparedPlan
+ */
+static SPIPlanPtr
+mv_FetchPreparedPlan(MV_QueryKey *key)
+{
+	MV_QueryHashEntry *entry;
+	SPIPlanPtr	plan;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Lookup for the key
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_FIND, NULL);
+	if (entry == NULL)
+		return NULL;
+
+	/*
+	 * Check whether the plan is still valid.  If it isn't, we don't want to
+	 * simply rely on plancache.c to regenerate it; rather we should start
+	 * from scratch and rebuild the query text too.  This is to cover cases
+	 * such as table/column renames.  We depend on the plancache machinery to
+	 * detect possible invalidations, though.
+	 *
+	 * CAUTION: this check is only trustworthy if the caller has already
+	 * locked both materialized views and base tables.
+	 *
+	 * Also, check whether the search_path is still the same as when we made it.
+	 * If it isn't, we need to rebuild the query text because the result of
+	 * pg_ivm_get_viewdef() will change.
+	 */
+	plan = entry->plan;
+	if (plan && SPI_plan_is_valid(plan) &&
+		SearchPathMatchesCurrentEnvironment(entry->search_path))
+		return plan;
+
+	/*
+	 * Otherwise we might as well flush the cached plan now, to free a little
+	 * memory space before we make a new one.
+	 */
+	if (plan)
+		SPI_freeplan(plan);
+	if (entry->search_path)
+		pfree(entry->search_path);
+
+	entry->plan = NULL;
+	entry->search_path = NULL;
+
+	return NULL;
+}
+
+/*
+ * mv_HashPreparedPlan
+ *
+ * Add another plan to our private SPI query plan hashtable.
+ */
+static void
+mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan)
+{
+	MV_QueryHashEntry *entry;
+	bool		found;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Add the new plan.  We might be overwriting an entry previously found
+	 * invalid by mv_FetchPreparedPlan.
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_ENTER, &found);
+	Assert(!found || entry->plan == NULL);
+	entry->plan = plan;
+	entry->search_path = GetSearchPathMatcher(TopMemoryContext);
+}
+
+/*
+ * mv_BuildQueryKey
+ *
+ * Construct a hashtable key for a prepared SPI plan for IVM.
+ */
+static void
+mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type)
+{
+	/*
+	 * We assume struct MV_QueryKey contains no padding bytes, else we'd need
+	 * to use memset to clear them.
+	 */
+	key->matview_id = matview_id;
+	key->query_type = query_type;
+}
+
 /*
  * AtAbort_IVM
  *
-- 
2.43.0


--Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ
Content-Type: text/x-diff;
 name="v38-0008-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v38-0008-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 259+ messages in thread

* [PATCH v37 09/11] Add support for min/max aggregates for IVM
@ 2023-05-31 11:58  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 259+ messages in thread

From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw)

Supporting min and max is more complicated than count, sum, or avg.

For an example of min, when tuples are inserted, the current min value
in the view and the min value in the inseteted tuples are compared,
then the smaller one is used as the latest min value. On the other
hand, when tuples are deleted, if the current min value in the view
equals to the min in the deleted tuples, we need re-computation the
latest min value from base tables. Otherwise, the current value in
the view remains.
---
 src/backend/commands/createas.c |  45 +++
 src/backend/commands/matview.c  | 644 +++++++++++++++++++++++++++++++-
 2 files changed, 680 insertions(+), 9 deletions(-)

diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 45a30309951..ed67f399b7c 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid)
 		case F_AVG_FLOAT8:
 		case F_AVG_INTERVAL:
 
+		/* min */
+		case F_MIN_ANYARRAY:
+		case F_MIN_INT8:
+		case F_MIN_INT4:
+		case F_MIN_INT2:
+		case F_MIN_OID:
+		case F_MIN_FLOAT4:
+		case F_MIN_FLOAT8:
+		case F_MIN_DATE:
+		case F_MIN_TIME:
+		case F_MIN_TIMETZ:
+		case F_MIN_MONEY:
+		case F_MIN_TIMESTAMP:
+		case F_MIN_TIMESTAMPTZ:
+		case F_MIN_INTERVAL:
+		case F_MIN_TEXT:
+		case F_MIN_NUMERIC:
+		case F_MIN_BPCHAR:
+		case F_MIN_TID:
+		case F_MIN_ANYENUM:
+		case F_MIN_INET:
+		case F_MIN_PG_LSN:
+
+		/* max */
+		case F_MAX_ANYARRAY:
+		case F_MAX_INT8:
+		case F_MAX_INT4:
+		case F_MAX_INT2:
+		case F_MAX_OID:
+		case F_MAX_FLOAT4:
+		case F_MAX_FLOAT8:
+		case F_MAX_DATE:
+		case F_MAX_TIME:
+		case F_MAX_TIMETZ:
+		case F_MAX_MONEY:
+		case F_MAX_TIMESTAMP:
+		case F_MAX_TIMESTAMPTZ:
+		case F_MAX_INTERVAL:
+		case F_MAX_TEXT:
+		case F_MAX_NUMERIC:
+		case F_MAX_BPCHAR:
+		case F_MAX_TID:
+		case F_MAX_ANYENUM:
+		case F_MAX_INET:
+		case F_MAX_PG_LSN:
 			return true;
 
 		default:
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 710224aa994..3b3871c49e2 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -69,6 +69,34 @@ typedef struct
 
 #define MV_INIT_QUERYHASHSIZE	16
 
+/* MV query type codes */
+#define MV_PLAN_RECALC			1
+#define MV_PLAN_SET_VALUE		2
+
+/*
+ * MI_QueryKey
+ *
+ * The key identifying a prepared SPI plan in our query hashtable
+ */
+typedef struct MV_QueryKey
+{
+	Oid			matview_id;	/* OID of materialized view */
+	int32		query_type;	/* query type ID, see MV_PLAN_XXX above */
+} MV_QueryKey;
+
+/*
+ * MV_QueryHashEntry
+ *
+ * Hash entry for cached plans used to maintain materialized views.
+ */
+typedef struct MV_QueryHashEntry
+{
+	MV_QueryKey key;
+	SPIPlanPtr	plan;
+	SearchPathMatcher *search_path;        /* search_path used for parsing
+											 * and planning */
+} MV_QueryHashEntry;
+
 /*
  * MV_TriggerHashEntry
  *
@@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo
 } DroppedImmvInfo;
 
 static HTAB *mv_trigger_info = NULL;
+static HTAB *mv_query_cache = NULL;
 static HTAB *dropped_immv = NULL;
 
 static HTAB *LastIvmUpdateHash;
@@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old,
 static void append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 						  StringInfo buf_new, StringInfo aggs_list,
 						  const char *aggtype);
+static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min);
 static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2,
 					 const char* count_col, const char *castType);
 static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
@@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old,
 				List *keys);
 static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname);
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc);
 static void apply_new_delta(const char *matviewname, const char *deltaname_new,
 				StringInfo target_list);
 static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
 				List *keys, StringInfo target_list, StringInfo aggs_set,
 				const char* count_colname);
 static char *get_matching_condition_string(List *keys);
+static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys);
+static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list);
+static char *get_select_for_recalc_string(List *keys);
+static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel);
+static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes);
+static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes);
 static void generate_equal(StringInfo querybuf, Oid opttype,
 			   const char *leftop, const char *rightop);
 
 static void mv_InitHashTables(void);
+static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key);
+static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan);
+static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type);
 static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
 									SubTransactionId subxid);
 static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
@@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	ListCell	*lc;
 	int			i;
 	List	   *keys = NIL;
+	List	   *minmax_list = NIL;
+	List	   *is_min_list = NIL;
 
 
 	/*
@@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 				append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf,
 										  format_type_be(aggref->aggtype));
 
+			/* min/max */
+			else if (!strcmp(aggname, "min") || !strcmp(aggname, "max"))
+			{
+				bool	is_min = (!strcmp(aggname, "min"));
+
+				append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min);
+
+				/* make a resname list of min and max aggregates */
+				minmax_list = lappend(minmax_list, resname);
+				is_min_list = lappend_int(is_min_list, is_min);
+			}
 			else
 				elog(ERROR, "unsupported aggregate function: %s", aggname);
 		}
@@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
 	{
 		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		SPITupleTable  *tuptable_recalc = NULL;
+		uint64			num_recalc;
 		int				rc;
 
 		/* convert tuplestores to ENR, and register for SPI */
@@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 			/* apply old delta and get rows to be recalculated */
 			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
 									   keys, aggs_list_buf, aggs_set_old,
-									   count_colname);
+									   minmax_list, is_min_list,
+									   count_colname, &tuptable_recalc, &num_recalc);
 		else
 			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
 
+		/*
+		 * If we have min or max, we might have to recalculate aggregate values from base tables
+		 * on some tuples. TIDs and keys such tuples are returned as a result of the above query.
+		 */
+		if (minmax_list && tuptable_recalc)
+			recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel);
+
 	}
 	/* For tuple insertion */
 	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
@@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 	);
 }
 
+/*
+ * append_set_clause_for_minmax
+ *
+ * Append SET clause string for min or max aggregation to given buffers.
+ * Also, append resnames required for calculating the aggregate value.
+ * is_min is true if this is min, false if not.
+ */
+static void
+append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min)
+{
+	char *count_col = IVM_colname("count", resname);
+
+	/* For tuple deletion */
+	if (buf_old)
+	{
+		/*
+		 * If the new value doesn't became NULL then use the value remaining
+		 * in the view although this will be recomputated afterwords.
+		 */
+		appendStringInfo(buf_old,
+			", %s = CASE WHEN %s THEN NULL ELSE %s END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_SUB, "mv", "t", count_col),
+			quote_qualified_identifier("mv", resname)
+		);
+		/* count = mv.count - t.count */
+		appendStringInfo(buf_old,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL)
+		);
+	}
+	/* For tuple insertion */
+	if (buf_new)
+	{
+		/*
+		 * min = LEAST(mv.min, diff.min)
+		 * max = GREATEST(mv.max, diff.max)
+		 */
+		appendStringInfo(buf_new,
+			", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_ADD, "mv", "diff", count_col),
+
+			is_min ? "LEAST" : "GREATEST",
+			quote_qualified_identifier("mv", resname),
+			quote_qualified_identifier("diff", resname)
+		);
+		/* count = mv.count + diff.count */
+		appendStringInfo(buf_new,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL)
+		);
+	}
+
+	appendStringInfo(aggs_list, ", %s, %s",
+		quote_qualified_identifier("diff", resname),
+		quote_qualified_identifier("diff", IVM_colname("count", resname))
+	);
+}
+
 /*
  * get_operation_string
  *
@@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
  * list to identify a tuple in the view. If the view has aggregates, this
  * requires strings representing resnames of aggregates and SET clause for
  * updating aggregate values.
+ *
+ * If the view has min or max aggregate, this requires a list of resnames of
+ * min/max aggregates and a list of boolean which represents which entries in
+ * minmax_list is min. These are necessary to check if we need to recalculate
+ * min or max aggregate values. In this case, this query returns TID and keys
+ * of tuples which need to be recalculated.  This result and the number of rows
+ * are stored in tuptables and num_recalc repectedly.
+ *
  */
 static void
 apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname)
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc)
 {
 	StringInfoData	querybuf;
 	char   *match_cond;
+	char   *updt_returning = "";
+	char   *select_for_recalc = "SELECT";
 	bool	agg_without_groupby = (list_length(keys) == 0);
 
+	Assert(tuptable_recalc != NULL);
+	Assert(num_recalc != NULL);
+
 	/* build WHERE condition for searching tuples to be deleted */
 	match_cond = get_matching_condition_string(keys);
 
+	/*
+	 * We need a special RETURNING clause and SELECT statement for min/max to
+	 * check which tuple needs re-calculation from base tables.
+	 */
+	if (minmax_list)
+	{
+		updt_returning = get_returning_string(minmax_list, is_min_list, keys);
+		select_for_recalc = get_select_for_recalc_string(keys);
+	}
+
 	/* Search for matching tuples from the view and update or delete if found. */
 	initStringInfo(&querybuf);
 	appendStringInfo(&querybuf,
@@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
 											"%s"	/* SET clauses for aggregates */
 						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
-					")"
-					/* delete a tuple if this is to be deleted */
-					"DELETE FROM %s AS mv USING t "
-					"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt",
+						"%s"						/* RETURNING clause for recalc infomation */
+					"), dlt AS ("			/* delete a tuple if this is to be deleted */
+						"DELETE FROM %s AS mv USING t "
+						"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt"
+					") %s",							/* SELECT returning which tuples need to be recalculated */
 					count_colname,
 					count_colname, count_colname, (agg_without_groupby ? "false" : "true"),
 					(aggs_list != NULL ? aggs_list->data : ""),
@@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 					match_cond,
 					matviewname, count_colname, count_colname, count_colname,
 					(aggs_set != NULL ? aggs_set->data : ""),
-					matviewname);
+					updt_returning,
+					matviewname,
+					select_for_recalc);
 
-	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT)
 		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+
+
+	/* Return tuples to be recalculated. */
+	if (minmax_list)
+	{
+		*tuptable_recalc = SPI_tuptable;
+		*num_recalc = SPI_processed;
+	}
+	else
+	{
+		*tuptable_recalc = NULL;
+		*num_recalc = 0;
+	}
 }
 
 /*
@@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys)
 	return match_cond.data;
 }
 
+/*
+ * get_returning_string
+ *
+ * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count.
+ * This clause returns ctid and a boolean value that indicates if we need to
+ * recalculate min or max value, for each updated row.
+ */
+static char *
+get_returning_string(List *minmax_list, List *is_min_list, List *keys)
+{
+	StringInfoData returning;
+	char		*recalc_cond;
+	ListCell	*lc;
+
+	Assert(minmax_list != NIL && is_min_list != NIL);
+	recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list);
+
+	initStringInfo(&returning);
+
+	appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char *resname = NameStr(attr->attname);
+		appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname));
+	}
+
+	return returning.data;
+}
+
+/*
+ * get_minmax_recalc_condition_string
+ *
+ * Build a predicate string for checking if any min/max aggregate
+ * value needs to be recalculated.
+ */
+static char *
+get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list)
+{
+	StringInfoData recalc_cond;
+	ListCell	*lc1, *lc2;
+
+	initStringInfo(&recalc_cond);
+
+	Assert (list_length(minmax_list) == list_length(is_min_list));
+
+	forboth (lc1, minmax_list, lc2, is_min_list)
+	{
+		char   *resname = (char *) lfirst(lc1);
+		bool	is_min = (bool) lfirst_int(lc2);
+		char   *op_str = (is_min ? ">=" : "<=");
+
+		appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s",
+			quote_qualified_identifier("mv", resname),
+			op_str,
+			quote_qualified_identifier("t", resname)
+		);
+
+		if (lnext(minmax_list, lc1))
+			appendStringInfo(&recalc_cond, " OR ");
+	}
+
+	return recalc_cond.data;
+}
+
+/*
+ * get_select_for_recalc_string
+ *
+ * Build a query to return tid and keys of tuples which need
+ * recalculation. This is used as the result of the query
+ * built by apply_old_delta.
+ */
+static char *
+get_select_for_recalc_string(List *keys)
+{
+	StringInfoData qry;
+	ListCell	*lc;
+
+	initStringInfo(&qry);
+
+	appendStringInfo(&qry, "SELECT tid");
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		appendStringInfo(&qry, ", %s", NameStr(attr->attname));
+	}
+
+	appendStringInfo(&qry, " FROM updt WHERE recalc");
+
+	return qry.data;
+}
+
+/*
+ * recalc_and_set_values
+ *
+ * Recalculate tuples in a materialized from base tables and update these.
+ * The tuples which needs recalculation are specified by keys, and resnames
+ * of columns to be updated are specified by namelist. TIDs and key values
+ * are given by tuples in tuptable_recalc. Its first attribute must be TID
+ * and key values must be following this.
+ */
+static void
+recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel)
+{
+	TupleDesc   tupdesc_recalc = tuptable_recalc->tupdesc;
+	Oid		   *keyTypes = NULL, *types = NULL;
+	char	   *keyNulls = NULL, *nulls = NULL;
+	Datum	   *keyVals = NULL, *vals = NULL;
+	int			num_vals = list_length(namelist);
+	int			num_keys = list_length(keys);
+	uint64      i;
+	Oid			matviewOid;
+	char	   *matviewname;
+
+	matviewOid = RelationGetRelid(matviewRel);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/* If we have keys, initialize arrays for them. */
+	if (keys)
+	{
+		keyTypes = palloc(sizeof(Oid) * num_keys);
+		keyNulls = palloc(sizeof(char) * num_keys);
+		keyVals = palloc(sizeof(Datum) * num_keys);
+		/* a tuple contains keys to be recalculated and ctid to be updated*/
+		Assert(tupdesc_recalc->natts == num_keys + 1);
+
+		/* Types of key attributes  */
+		for (i = 0; i < num_keys; i++)
+			keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid;
+	}
+
+	/* allocate memory for all attribute names and tid */
+	types = palloc(sizeof(Oid) * (num_vals + 1));
+	nulls = palloc(sizeof(char) * (num_vals + 1));
+	vals = palloc(sizeof(Datum) * (num_vals + 1));
+
+	/* For each tuple which needs recalculation */
+	for (i = 0; i < num_tuples; i++)
+	{
+		int j;
+		bool isnull;
+		SPIPlanPtr plan;
+		SPITupleTable *tuptable_newvals;
+		TupleDesc   tupdesc_newvals;
+
+		/* Set group key values as parameters if needed. */
+		if (keys)
+		{
+			for (j = 0; j < num_keys; j++)
+			{
+				keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull);
+				if (isnull)
+					keyNulls[j] = 'n';
+				else
+					keyNulls[j] = ' ';
+			}
+		}
+
+		/*
+		 * Get recalculated values from base tables. The result must be
+		 * only one tuple thich contains the new values for specified keys.
+		 */
+		plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes);
+		if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT)
+			elog(ERROR, "SPI_execute_plan");
+		if (SPI_processed != 1)
+			elog(ERROR, "SPI_execute_plan returned zero or more than one rows");
+
+		tuptable_newvals = SPI_tuptable;
+		tupdesc_newvals = tuptable_newvals->tupdesc;
+
+		Assert(tupdesc_newvals->natts == num_vals);
+
+		/* Set the new values as parameters */
+		for (j = 0; j < tupdesc_newvals->natts; j++)
+		{
+			if (i == 0)
+				types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid;
+
+			vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull);
+			if (isnull)
+				nulls[j] = 'n';
+			else
+				nulls[j] = ' ';
+		}
+		/* Set TID of the view tuple to be updated as a parameter */
+		types[j] = TIDOID;
+		vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull);
+		nulls[j] = ' ';
+
+		/* Update the view tuple to the new values */
+		plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types);
+		if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE)
+			elog(ERROR, "SPI_execute_plan");
+	}
+}
+
+
+/*
+ * get_plan_for_recalc
+ *
+ * Create or fetch a plan for recalculating value in the view's target list
+ * from base tables using the definition query of materialized view specified
+ * by matviewOid. namelist is a list of resnames of values to be recalculated.
+ *
+ * keys is a list of keys to identify tuples to be recalculated if this is not
+ * empty. KeyTypes is an array of types of keys.
+ */
+static SPIPlanPtr
+get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes)
+{
+	MV_QueryKey hash_key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the recalculation */
+	mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC);
+	if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL)
+	{
+		ListCell	   *lc;
+		StringInfoData	str;
+		char   *viewdef;
+
+		/* get view definition of matview */
+		viewdef = text_to_cstring((text *) DatumGetPointer(
+					DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid))));
+		/* get rid of trailing semi-colon */
+		viewdef[strlen(viewdef)-1] = '\0';
+
+		/*
+		 * Build a query string for recalculating values. This is like
+		 *
+		 *  SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv
+		 *   WHERE (key1, key2, ...) = ($1, $2, ...);
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "SELECT ");
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, " FROM (%s) mv", viewdef);
+
+		if (keys)
+		{
+			int		i = 1;
+			char	paramname[16];
+
+			appendStringInfo(&str, " WHERE (");
+			foreach (lc, keys)
+			{
+				Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+				char   *resname = NameStr(attr->attname);
+				Oid		typid = attr->atttypid;
+
+				sprintf(paramname, "$%d", i);
+				appendStringInfo(&str, "(");
+				generate_equal(&str, typid, resname, paramname);
+				appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))",
+								 resname, paramname);
+
+				if (lnext(keys, lc))
+					appendStringInfoString(&str, " AND ");
+				i++;
+			}
+			appendStringInfo(&str, ")");
+		}
+		else
+			keyTypes = NULL;
+
+		plan = SPI_prepare(str.data, list_length(keys), keyTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&hash_key, plan);
+	}
+
+	return plan;
+}
+
+/*
+ * get_plan_for_set_values
+ *
+ * Create or fetch a plan for applying new values calculated by
+ * get_plan_for_recalc to a materialized view specified by matviewOid.
+ * matviewname is the name of the view.  namelist is a list of resnames
+ * of attributes to be updated, and valTypes is an array of types of the
+ * values.
+ */
+static SPIPlanPtr
+get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes)
+{
+	MV_QueryKey	key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the real check */
+	mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE);
+	if ((plan = mv_FetchPreparedPlan(&key)) == NULL)
+	{
+		ListCell	  *lc;
+		StringInfoData str;
+		int		i;
+
+		/*
+		 * Build a query string for applying min/max values. This is like
+		 *
+		 *  UPDATE matviewname AS mv
+		 *   SET (x1, x2, x3, x4) = ($1, $2, $3, $4)
+		 *   WHERE ctid = $5;
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname);
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, ") = ROW(");
+
+		for (i = 1; i <= list_length(namelist); i++)
+			appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i);
+
+		appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i);
+
+		plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&key, plan);
+	}
+
+	return plan;
+}
+
 /*
  * generate_equals
  *
@@ -3025,6 +3541,13 @@ mv_InitHashTables(void)
 {
 	HASHCTL		ctl;
 
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(MV_QueryKey);
+	ctl.entrysize = sizeof(MV_QueryHashEntry);
+	mv_query_cache = hash_create("MV query cache",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
 	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(MV_TriggerHashEntry);
@@ -3039,6 +3562,109 @@ mv_InitHashTables(void)
 							   &ctl, HASH_ELEM | HASH_BLOBS);
 }
 
+/*
+ * mv_FetchPreparedPlan
+ */
+static SPIPlanPtr
+mv_FetchPreparedPlan(MV_QueryKey *key)
+{
+	MV_QueryHashEntry *entry;
+	SPIPlanPtr	plan;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Lookup for the key
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_FIND, NULL);
+	if (entry == NULL)
+		return NULL;
+
+	/*
+	 * Check whether the plan is still valid.  If it isn't, we don't want to
+	 * simply rely on plancache.c to regenerate it; rather we should start
+	 * from scratch and rebuild the query text too.  This is to cover cases
+	 * such as table/column renames.  We depend on the plancache machinery to
+	 * detect possible invalidations, though.
+	 *
+	 * CAUTION: this check is only trustworthy if the caller has already
+	 * locked both materialized views and base tables.
+	 *
+	 * Also, check whether the search_path is still the same as when we made it.
+	 * If it isn't, we need to rebuild the query text because the result of
+	 * pg_ivm_get_viewdef() will change.
+	 */
+	plan = entry->plan;
+	if (plan && SPI_plan_is_valid(plan) &&
+		SearchPathMatchesCurrentEnvironment(entry->search_path))
+		return plan;
+
+	/*
+	 * Otherwise we might as well flush the cached plan now, to free a little
+	 * memory space before we make a new one.
+	 */
+	if (plan)
+		SPI_freeplan(plan);
+	if (entry->search_path)
+		pfree(entry->search_path);
+
+	entry->plan = NULL;
+	entry->search_path = NULL;
+
+	return NULL;
+}
+
+/*
+ * mv_HashPreparedPlan
+ *
+ * Add another plan to our private SPI query plan hashtable.
+ */
+static void
+mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan)
+{
+	MV_QueryHashEntry *entry;
+	bool		found;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Add the new plan.  We might be overwriting an entry previously found
+	 * invalid by mv_FetchPreparedPlan.
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_ENTER, &found);
+	Assert(!found || entry->plan == NULL);
+	entry->plan = plan;
+	entry->search_path = GetSearchPathMatcher(TopMemoryContext);
+}
+
+/*
+ * mv_BuildQueryKey
+ *
+ * Construct a hashtable key for a prepared SPI plan for IVM.
+ */
+static void
+mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type)
+{
+	/*
+	 * We assume struct MV_QueryKey contains no padding bytes, else we'd need
+	 * to use memset to clear them.
+	 */
+	key->matview_id = matview_id;
+	key->query_type = query_type;
+}
+
 /*
  * AtAbort_IVM
  *
-- 
2.43.0


--Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd
Content-Type: text/x-diff;
 name="v37-0008-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v37-0008-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 259+ messages in thread

* [PATCH v38 09/11] Add support for min/max aggregates for IVM
@ 2023-05-31 11:58  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 259+ messages in thread

From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw)

Supporting min and max is more complicated than count, sum, or avg.

For an example of min, when tuples are inserted, the current min value
in the view and the min value in the inseteted tuples are compared,
then the smaller one is used as the latest min value. On the other
hand, when tuples are deleted, if the current min value in the view
equals to the min in the deleted tuples, we need re-computation the
latest min value from base tables. Otherwise, the current value in
the view remains.
---
 src/backend/commands/createas.c |  45 +++
 src/backend/commands/matview.c  | 644 +++++++++++++++++++++++++++++++-
 2 files changed, 680 insertions(+), 9 deletions(-)

diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 35e124694ab..540d9e3d5c8 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid)
 		case F_AVG_FLOAT8:
 		case F_AVG_INTERVAL:
 
+		/* min */
+		case F_MIN_ANYARRAY:
+		case F_MIN_INT8:
+		case F_MIN_INT4:
+		case F_MIN_INT2:
+		case F_MIN_OID:
+		case F_MIN_FLOAT4:
+		case F_MIN_FLOAT8:
+		case F_MIN_DATE:
+		case F_MIN_TIME:
+		case F_MIN_TIMETZ:
+		case F_MIN_MONEY:
+		case F_MIN_TIMESTAMP:
+		case F_MIN_TIMESTAMPTZ:
+		case F_MIN_INTERVAL:
+		case F_MIN_TEXT:
+		case F_MIN_NUMERIC:
+		case F_MIN_BPCHAR:
+		case F_MIN_TID:
+		case F_MIN_ANYENUM:
+		case F_MIN_INET:
+		case F_MIN_PG_LSN:
+
+		/* max */
+		case F_MAX_ANYARRAY:
+		case F_MAX_INT8:
+		case F_MAX_INT4:
+		case F_MAX_INT2:
+		case F_MAX_OID:
+		case F_MAX_FLOAT4:
+		case F_MAX_FLOAT8:
+		case F_MAX_DATE:
+		case F_MAX_TIME:
+		case F_MAX_TIMETZ:
+		case F_MAX_MONEY:
+		case F_MAX_TIMESTAMP:
+		case F_MAX_TIMESTAMPTZ:
+		case F_MAX_INTERVAL:
+		case F_MAX_TEXT:
+		case F_MAX_NUMERIC:
+		case F_MAX_BPCHAR:
+		case F_MAX_TID:
+		case F_MAX_ANYENUM:
+		case F_MAX_INET:
+		case F_MAX_PG_LSN:
 			return true;
 
 		default:
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 710224aa994..3b3871c49e2 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -69,6 +69,34 @@ typedef struct
 
 #define MV_INIT_QUERYHASHSIZE	16
 
+/* MV query type codes */
+#define MV_PLAN_RECALC			1
+#define MV_PLAN_SET_VALUE		2
+
+/*
+ * MI_QueryKey
+ *
+ * The key identifying a prepared SPI plan in our query hashtable
+ */
+typedef struct MV_QueryKey
+{
+	Oid			matview_id;	/* OID of materialized view */
+	int32		query_type;	/* query type ID, see MV_PLAN_XXX above */
+} MV_QueryKey;
+
+/*
+ * MV_QueryHashEntry
+ *
+ * Hash entry for cached plans used to maintain materialized views.
+ */
+typedef struct MV_QueryHashEntry
+{
+	MV_QueryKey key;
+	SPIPlanPtr	plan;
+	SearchPathMatcher *search_path;        /* search_path used for parsing
+											 * and planning */
+} MV_QueryHashEntry;
+
 /*
  * MV_TriggerHashEntry
  *
@@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo
 } DroppedImmvInfo;
 
 static HTAB *mv_trigger_info = NULL;
+static HTAB *mv_query_cache = NULL;
 static HTAB *dropped_immv = NULL;
 
 static HTAB *LastIvmUpdateHash;
@@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old,
 static void append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 						  StringInfo buf_new, StringInfo aggs_list,
 						  const char *aggtype);
+static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min);
 static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2,
 					 const char* count_col, const char *castType);
 static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
@@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old,
 				List *keys);
 static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname);
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc);
 static void apply_new_delta(const char *matviewname, const char *deltaname_new,
 				StringInfo target_list);
 static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
 				List *keys, StringInfo target_list, StringInfo aggs_set,
 				const char* count_colname);
 static char *get_matching_condition_string(List *keys);
+static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys);
+static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list);
+static char *get_select_for_recalc_string(List *keys);
+static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel);
+static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes);
+static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes);
 static void generate_equal(StringInfo querybuf, Oid opttype,
 			   const char *leftop, const char *rightop);
 
 static void mv_InitHashTables(void);
+static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key);
+static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan);
+static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type);
 static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
 									SubTransactionId subxid);
 static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
@@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	ListCell	*lc;
 	int			i;
 	List	   *keys = NIL;
+	List	   *minmax_list = NIL;
+	List	   *is_min_list = NIL;
 
 
 	/*
@@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 				append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf,
 										  format_type_be(aggref->aggtype));
 
+			/* min/max */
+			else if (!strcmp(aggname, "min") || !strcmp(aggname, "max"))
+			{
+				bool	is_min = (!strcmp(aggname, "min"));
+
+				append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min);
+
+				/* make a resname list of min and max aggregates */
+				minmax_list = lappend(minmax_list, resname);
+				is_min_list = lappend_int(is_min_list, is_min);
+			}
 			else
 				elog(ERROR, "unsupported aggregate function: %s", aggname);
 		}
@@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
 	{
 		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		SPITupleTable  *tuptable_recalc = NULL;
+		uint64			num_recalc;
 		int				rc;
 
 		/* convert tuplestores to ENR, and register for SPI */
@@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 			/* apply old delta and get rows to be recalculated */
 			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
 									   keys, aggs_list_buf, aggs_set_old,
-									   count_colname);
+									   minmax_list, is_min_list,
+									   count_colname, &tuptable_recalc, &num_recalc);
 		else
 			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
 
+		/*
+		 * If we have min or max, we might have to recalculate aggregate values from base tables
+		 * on some tuples. TIDs and keys such tuples are returned as a result of the above query.
+		 */
+		if (minmax_list && tuptable_recalc)
+			recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel);
+
 	}
 	/* For tuple insertion */
 	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
@@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 	);
 }
 
+/*
+ * append_set_clause_for_minmax
+ *
+ * Append SET clause string for min or max aggregation to given buffers.
+ * Also, append resnames required for calculating the aggregate value.
+ * is_min is true if this is min, false if not.
+ */
+static void
+append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min)
+{
+	char *count_col = IVM_colname("count", resname);
+
+	/* For tuple deletion */
+	if (buf_old)
+	{
+		/*
+		 * If the new value doesn't became NULL then use the value remaining
+		 * in the view although this will be recomputated afterwords.
+		 */
+		appendStringInfo(buf_old,
+			", %s = CASE WHEN %s THEN NULL ELSE %s END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_SUB, "mv", "t", count_col),
+			quote_qualified_identifier("mv", resname)
+		);
+		/* count = mv.count - t.count */
+		appendStringInfo(buf_old,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL)
+		);
+	}
+	/* For tuple insertion */
+	if (buf_new)
+	{
+		/*
+		 * min = LEAST(mv.min, diff.min)
+		 * max = GREATEST(mv.max, diff.max)
+		 */
+		appendStringInfo(buf_new,
+			", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_ADD, "mv", "diff", count_col),
+
+			is_min ? "LEAST" : "GREATEST",
+			quote_qualified_identifier("mv", resname),
+			quote_qualified_identifier("diff", resname)
+		);
+		/* count = mv.count + diff.count */
+		appendStringInfo(buf_new,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL)
+		);
+	}
+
+	appendStringInfo(aggs_list, ", %s, %s",
+		quote_qualified_identifier("diff", resname),
+		quote_qualified_identifier("diff", IVM_colname("count", resname))
+	);
+}
+
 /*
  * get_operation_string
  *
@@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
  * list to identify a tuple in the view. If the view has aggregates, this
  * requires strings representing resnames of aggregates and SET clause for
  * updating aggregate values.
+ *
+ * If the view has min or max aggregate, this requires a list of resnames of
+ * min/max aggregates and a list of boolean which represents which entries in
+ * minmax_list is min. These are necessary to check if we need to recalculate
+ * min or max aggregate values. In this case, this query returns TID and keys
+ * of tuples which need to be recalculated.  This result and the number of rows
+ * are stored in tuptables and num_recalc repectedly.
+ *
  */
 static void
 apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname)
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc)
 {
 	StringInfoData	querybuf;
 	char   *match_cond;
+	char   *updt_returning = "";
+	char   *select_for_recalc = "SELECT";
 	bool	agg_without_groupby = (list_length(keys) == 0);
 
+	Assert(tuptable_recalc != NULL);
+	Assert(num_recalc != NULL);
+
 	/* build WHERE condition for searching tuples to be deleted */
 	match_cond = get_matching_condition_string(keys);
 
+	/*
+	 * We need a special RETURNING clause and SELECT statement for min/max to
+	 * check which tuple needs re-calculation from base tables.
+	 */
+	if (minmax_list)
+	{
+		updt_returning = get_returning_string(minmax_list, is_min_list, keys);
+		select_for_recalc = get_select_for_recalc_string(keys);
+	}
+
 	/* Search for matching tuples from the view and update or delete if found. */
 	initStringInfo(&querybuf);
 	appendStringInfo(&querybuf,
@@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
 											"%s"	/* SET clauses for aggregates */
 						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
-					")"
-					/* delete a tuple if this is to be deleted */
-					"DELETE FROM %s AS mv USING t "
-					"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt",
+						"%s"						/* RETURNING clause for recalc infomation */
+					"), dlt AS ("			/* delete a tuple if this is to be deleted */
+						"DELETE FROM %s AS mv USING t "
+						"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt"
+					") %s",							/* SELECT returning which tuples need to be recalculated */
 					count_colname,
 					count_colname, count_colname, (agg_without_groupby ? "false" : "true"),
 					(aggs_list != NULL ? aggs_list->data : ""),
@@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 					match_cond,
 					matviewname, count_colname, count_colname, count_colname,
 					(aggs_set != NULL ? aggs_set->data : ""),
-					matviewname);
+					updt_returning,
+					matviewname,
+					select_for_recalc);
 
-	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT)
 		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+
+
+	/* Return tuples to be recalculated. */
+	if (minmax_list)
+	{
+		*tuptable_recalc = SPI_tuptable;
+		*num_recalc = SPI_processed;
+	}
+	else
+	{
+		*tuptable_recalc = NULL;
+		*num_recalc = 0;
+	}
 }
 
 /*
@@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys)
 	return match_cond.data;
 }
 
+/*
+ * get_returning_string
+ *
+ * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count.
+ * This clause returns ctid and a boolean value that indicates if we need to
+ * recalculate min or max value, for each updated row.
+ */
+static char *
+get_returning_string(List *minmax_list, List *is_min_list, List *keys)
+{
+	StringInfoData returning;
+	char		*recalc_cond;
+	ListCell	*lc;
+
+	Assert(minmax_list != NIL && is_min_list != NIL);
+	recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list);
+
+	initStringInfo(&returning);
+
+	appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char *resname = NameStr(attr->attname);
+		appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname));
+	}
+
+	return returning.data;
+}
+
+/*
+ * get_minmax_recalc_condition_string
+ *
+ * Build a predicate string for checking if any min/max aggregate
+ * value needs to be recalculated.
+ */
+static char *
+get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list)
+{
+	StringInfoData recalc_cond;
+	ListCell	*lc1, *lc2;
+
+	initStringInfo(&recalc_cond);
+
+	Assert (list_length(minmax_list) == list_length(is_min_list));
+
+	forboth (lc1, minmax_list, lc2, is_min_list)
+	{
+		char   *resname = (char *) lfirst(lc1);
+		bool	is_min = (bool) lfirst_int(lc2);
+		char   *op_str = (is_min ? ">=" : "<=");
+
+		appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s",
+			quote_qualified_identifier("mv", resname),
+			op_str,
+			quote_qualified_identifier("t", resname)
+		);
+
+		if (lnext(minmax_list, lc1))
+			appendStringInfo(&recalc_cond, " OR ");
+	}
+
+	return recalc_cond.data;
+}
+
+/*
+ * get_select_for_recalc_string
+ *
+ * Build a query to return tid and keys of tuples which need
+ * recalculation. This is used as the result of the query
+ * built by apply_old_delta.
+ */
+static char *
+get_select_for_recalc_string(List *keys)
+{
+	StringInfoData qry;
+	ListCell	*lc;
+
+	initStringInfo(&qry);
+
+	appendStringInfo(&qry, "SELECT tid");
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		appendStringInfo(&qry, ", %s", NameStr(attr->attname));
+	}
+
+	appendStringInfo(&qry, " FROM updt WHERE recalc");
+
+	return qry.data;
+}
+
+/*
+ * recalc_and_set_values
+ *
+ * Recalculate tuples in a materialized from base tables and update these.
+ * The tuples which needs recalculation are specified by keys, and resnames
+ * of columns to be updated are specified by namelist. TIDs and key values
+ * are given by tuples in tuptable_recalc. Its first attribute must be TID
+ * and key values must be following this.
+ */
+static void
+recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel)
+{
+	TupleDesc   tupdesc_recalc = tuptable_recalc->tupdesc;
+	Oid		   *keyTypes = NULL, *types = NULL;
+	char	   *keyNulls = NULL, *nulls = NULL;
+	Datum	   *keyVals = NULL, *vals = NULL;
+	int			num_vals = list_length(namelist);
+	int			num_keys = list_length(keys);
+	uint64      i;
+	Oid			matviewOid;
+	char	   *matviewname;
+
+	matviewOid = RelationGetRelid(matviewRel);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/* If we have keys, initialize arrays for them. */
+	if (keys)
+	{
+		keyTypes = palloc(sizeof(Oid) * num_keys);
+		keyNulls = palloc(sizeof(char) * num_keys);
+		keyVals = palloc(sizeof(Datum) * num_keys);
+		/* a tuple contains keys to be recalculated and ctid to be updated*/
+		Assert(tupdesc_recalc->natts == num_keys + 1);
+
+		/* Types of key attributes  */
+		for (i = 0; i < num_keys; i++)
+			keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid;
+	}
+
+	/* allocate memory for all attribute names and tid */
+	types = palloc(sizeof(Oid) * (num_vals + 1));
+	nulls = palloc(sizeof(char) * (num_vals + 1));
+	vals = palloc(sizeof(Datum) * (num_vals + 1));
+
+	/* For each tuple which needs recalculation */
+	for (i = 0; i < num_tuples; i++)
+	{
+		int j;
+		bool isnull;
+		SPIPlanPtr plan;
+		SPITupleTable *tuptable_newvals;
+		TupleDesc   tupdesc_newvals;
+
+		/* Set group key values as parameters if needed. */
+		if (keys)
+		{
+			for (j = 0; j < num_keys; j++)
+			{
+				keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull);
+				if (isnull)
+					keyNulls[j] = 'n';
+				else
+					keyNulls[j] = ' ';
+			}
+		}
+
+		/*
+		 * Get recalculated values from base tables. The result must be
+		 * only one tuple thich contains the new values for specified keys.
+		 */
+		plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes);
+		if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT)
+			elog(ERROR, "SPI_execute_plan");
+		if (SPI_processed != 1)
+			elog(ERROR, "SPI_execute_plan returned zero or more than one rows");
+
+		tuptable_newvals = SPI_tuptable;
+		tupdesc_newvals = tuptable_newvals->tupdesc;
+
+		Assert(tupdesc_newvals->natts == num_vals);
+
+		/* Set the new values as parameters */
+		for (j = 0; j < tupdesc_newvals->natts; j++)
+		{
+			if (i == 0)
+				types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid;
+
+			vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull);
+			if (isnull)
+				nulls[j] = 'n';
+			else
+				nulls[j] = ' ';
+		}
+		/* Set TID of the view tuple to be updated as a parameter */
+		types[j] = TIDOID;
+		vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull);
+		nulls[j] = ' ';
+
+		/* Update the view tuple to the new values */
+		plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types);
+		if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE)
+			elog(ERROR, "SPI_execute_plan");
+	}
+}
+
+
+/*
+ * get_plan_for_recalc
+ *
+ * Create or fetch a plan for recalculating value in the view's target list
+ * from base tables using the definition query of materialized view specified
+ * by matviewOid. namelist is a list of resnames of values to be recalculated.
+ *
+ * keys is a list of keys to identify tuples to be recalculated if this is not
+ * empty. KeyTypes is an array of types of keys.
+ */
+static SPIPlanPtr
+get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes)
+{
+	MV_QueryKey hash_key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the recalculation */
+	mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC);
+	if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL)
+	{
+		ListCell	   *lc;
+		StringInfoData	str;
+		char   *viewdef;
+
+		/* get view definition of matview */
+		viewdef = text_to_cstring((text *) DatumGetPointer(
+					DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid))));
+		/* get rid of trailing semi-colon */
+		viewdef[strlen(viewdef)-1] = '\0';
+
+		/*
+		 * Build a query string for recalculating values. This is like
+		 *
+		 *  SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv
+		 *   WHERE (key1, key2, ...) = ($1, $2, ...);
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "SELECT ");
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, " FROM (%s) mv", viewdef);
+
+		if (keys)
+		{
+			int		i = 1;
+			char	paramname[16];
+
+			appendStringInfo(&str, " WHERE (");
+			foreach (lc, keys)
+			{
+				Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+				char   *resname = NameStr(attr->attname);
+				Oid		typid = attr->atttypid;
+
+				sprintf(paramname, "$%d", i);
+				appendStringInfo(&str, "(");
+				generate_equal(&str, typid, resname, paramname);
+				appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))",
+								 resname, paramname);
+
+				if (lnext(keys, lc))
+					appendStringInfoString(&str, " AND ");
+				i++;
+			}
+			appendStringInfo(&str, ")");
+		}
+		else
+			keyTypes = NULL;
+
+		plan = SPI_prepare(str.data, list_length(keys), keyTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&hash_key, plan);
+	}
+
+	return plan;
+}
+
+/*
+ * get_plan_for_set_values
+ *
+ * Create or fetch a plan for applying new values calculated by
+ * get_plan_for_recalc to a materialized view specified by matviewOid.
+ * matviewname is the name of the view.  namelist is a list of resnames
+ * of attributes to be updated, and valTypes is an array of types of the
+ * values.
+ */
+static SPIPlanPtr
+get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes)
+{
+	MV_QueryKey	key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the real check */
+	mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE);
+	if ((plan = mv_FetchPreparedPlan(&key)) == NULL)
+	{
+		ListCell	  *lc;
+		StringInfoData str;
+		int		i;
+
+		/*
+		 * Build a query string for applying min/max values. This is like
+		 *
+		 *  UPDATE matviewname AS mv
+		 *   SET (x1, x2, x3, x4) = ($1, $2, $3, $4)
+		 *   WHERE ctid = $5;
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname);
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, ") = ROW(");
+
+		for (i = 1; i <= list_length(namelist); i++)
+			appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i);
+
+		appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i);
+
+		plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&key, plan);
+	}
+
+	return plan;
+}
+
 /*
  * generate_equals
  *
@@ -3025,6 +3541,13 @@ mv_InitHashTables(void)
 {
 	HASHCTL		ctl;
 
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(MV_QueryKey);
+	ctl.entrysize = sizeof(MV_QueryHashEntry);
+	mv_query_cache = hash_create("MV query cache",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
 	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(MV_TriggerHashEntry);
@@ -3039,6 +3562,109 @@ mv_InitHashTables(void)
 							   &ctl, HASH_ELEM | HASH_BLOBS);
 }
 
+/*
+ * mv_FetchPreparedPlan
+ */
+static SPIPlanPtr
+mv_FetchPreparedPlan(MV_QueryKey *key)
+{
+	MV_QueryHashEntry *entry;
+	SPIPlanPtr	plan;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Lookup for the key
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_FIND, NULL);
+	if (entry == NULL)
+		return NULL;
+
+	/*
+	 * Check whether the plan is still valid.  If it isn't, we don't want to
+	 * simply rely on plancache.c to regenerate it; rather we should start
+	 * from scratch and rebuild the query text too.  This is to cover cases
+	 * such as table/column renames.  We depend on the plancache machinery to
+	 * detect possible invalidations, though.
+	 *
+	 * CAUTION: this check is only trustworthy if the caller has already
+	 * locked both materialized views and base tables.
+	 *
+	 * Also, check whether the search_path is still the same as when we made it.
+	 * If it isn't, we need to rebuild the query text because the result of
+	 * pg_ivm_get_viewdef() will change.
+	 */
+	plan = entry->plan;
+	if (plan && SPI_plan_is_valid(plan) &&
+		SearchPathMatchesCurrentEnvironment(entry->search_path))
+		return plan;
+
+	/*
+	 * Otherwise we might as well flush the cached plan now, to free a little
+	 * memory space before we make a new one.
+	 */
+	if (plan)
+		SPI_freeplan(plan);
+	if (entry->search_path)
+		pfree(entry->search_path);
+
+	entry->plan = NULL;
+	entry->search_path = NULL;
+
+	return NULL;
+}
+
+/*
+ * mv_HashPreparedPlan
+ *
+ * Add another plan to our private SPI query plan hashtable.
+ */
+static void
+mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan)
+{
+	MV_QueryHashEntry *entry;
+	bool		found;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Add the new plan.  We might be overwriting an entry previously found
+	 * invalid by mv_FetchPreparedPlan.
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_ENTER, &found);
+	Assert(!found || entry->plan == NULL);
+	entry->plan = plan;
+	entry->search_path = GetSearchPathMatcher(TopMemoryContext);
+}
+
+/*
+ * mv_BuildQueryKey
+ *
+ * Construct a hashtable key for a prepared SPI plan for IVM.
+ */
+static void
+mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type)
+{
+	/*
+	 * We assume struct MV_QueryKey contains no padding bytes, else we'd need
+	 * to use memset to clear them.
+	 */
+	key->matview_id = matview_id;
+	key->query_type = query_type;
+}
+
 /*
  * AtAbort_IVM
  *
-- 
2.43.0


--Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ
Content-Type: text/x-diff;
 name="v38-0008-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v38-0008-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 259+ messages in thread

* [PATCH v37 09/11] Add support for min/max aggregates for IVM
@ 2023-05-31 11:58  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 259+ messages in thread

From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw)

Supporting min and max is more complicated than count, sum, or avg.

For an example of min, when tuples are inserted, the current min value
in the view and the min value in the inseteted tuples are compared,
then the smaller one is used as the latest min value. On the other
hand, when tuples are deleted, if the current min value in the view
equals to the min in the deleted tuples, we need re-computation the
latest min value from base tables. Otherwise, the current value in
the view remains.
---
 src/backend/commands/createas.c |  45 +++
 src/backend/commands/matview.c  | 644 +++++++++++++++++++++++++++++++-
 2 files changed, 680 insertions(+), 9 deletions(-)

diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 45a30309951..ed67f399b7c 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid)
 		case F_AVG_FLOAT8:
 		case F_AVG_INTERVAL:
 
+		/* min */
+		case F_MIN_ANYARRAY:
+		case F_MIN_INT8:
+		case F_MIN_INT4:
+		case F_MIN_INT2:
+		case F_MIN_OID:
+		case F_MIN_FLOAT4:
+		case F_MIN_FLOAT8:
+		case F_MIN_DATE:
+		case F_MIN_TIME:
+		case F_MIN_TIMETZ:
+		case F_MIN_MONEY:
+		case F_MIN_TIMESTAMP:
+		case F_MIN_TIMESTAMPTZ:
+		case F_MIN_INTERVAL:
+		case F_MIN_TEXT:
+		case F_MIN_NUMERIC:
+		case F_MIN_BPCHAR:
+		case F_MIN_TID:
+		case F_MIN_ANYENUM:
+		case F_MIN_INET:
+		case F_MIN_PG_LSN:
+
+		/* max */
+		case F_MAX_ANYARRAY:
+		case F_MAX_INT8:
+		case F_MAX_INT4:
+		case F_MAX_INT2:
+		case F_MAX_OID:
+		case F_MAX_FLOAT4:
+		case F_MAX_FLOAT8:
+		case F_MAX_DATE:
+		case F_MAX_TIME:
+		case F_MAX_TIMETZ:
+		case F_MAX_MONEY:
+		case F_MAX_TIMESTAMP:
+		case F_MAX_TIMESTAMPTZ:
+		case F_MAX_INTERVAL:
+		case F_MAX_TEXT:
+		case F_MAX_NUMERIC:
+		case F_MAX_BPCHAR:
+		case F_MAX_TID:
+		case F_MAX_ANYENUM:
+		case F_MAX_INET:
+		case F_MAX_PG_LSN:
 			return true;
 
 		default:
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 710224aa994..3b3871c49e2 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -69,6 +69,34 @@ typedef struct
 
 #define MV_INIT_QUERYHASHSIZE	16
 
+/* MV query type codes */
+#define MV_PLAN_RECALC			1
+#define MV_PLAN_SET_VALUE		2
+
+/*
+ * MI_QueryKey
+ *
+ * The key identifying a prepared SPI plan in our query hashtable
+ */
+typedef struct MV_QueryKey
+{
+	Oid			matview_id;	/* OID of materialized view */
+	int32		query_type;	/* query type ID, see MV_PLAN_XXX above */
+} MV_QueryKey;
+
+/*
+ * MV_QueryHashEntry
+ *
+ * Hash entry for cached plans used to maintain materialized views.
+ */
+typedef struct MV_QueryHashEntry
+{
+	MV_QueryKey key;
+	SPIPlanPtr	plan;
+	SearchPathMatcher *search_path;        /* search_path used for parsing
+											 * and planning */
+} MV_QueryHashEntry;
+
 /*
  * MV_TriggerHashEntry
  *
@@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo
 } DroppedImmvInfo;
 
 static HTAB *mv_trigger_info = NULL;
+static HTAB *mv_query_cache = NULL;
 static HTAB *dropped_immv = NULL;
 
 static HTAB *LastIvmUpdateHash;
@@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old,
 static void append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 						  StringInfo buf_new, StringInfo aggs_list,
 						  const char *aggtype);
+static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min);
 static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2,
 					 const char* count_col, const char *castType);
 static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
@@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old,
 				List *keys);
 static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname);
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc);
 static void apply_new_delta(const char *matviewname, const char *deltaname_new,
 				StringInfo target_list);
 static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
 				List *keys, StringInfo target_list, StringInfo aggs_set,
 				const char* count_colname);
 static char *get_matching_condition_string(List *keys);
+static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys);
+static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list);
+static char *get_select_for_recalc_string(List *keys);
+static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel);
+static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes);
+static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes);
 static void generate_equal(StringInfo querybuf, Oid opttype,
 			   const char *leftop, const char *rightop);
 
 static void mv_InitHashTables(void);
+static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key);
+static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan);
+static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type);
 static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort,
 									SubTransactionId subxid);
 static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid);
@@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	ListCell	*lc;
 	int			i;
 	List	   *keys = NIL;
+	List	   *minmax_list = NIL;
+	List	   *is_min_list = NIL;
 
 
 	/*
@@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 				append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf,
 										  format_type_be(aggref->aggtype));
 
+			/* min/max */
+			else if (!strcmp(aggname, "min") || !strcmp(aggname, "max"))
+			{
+				bool	is_min = (!strcmp(aggname, "min"));
+
+				append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min);
+
+				/* make a resname list of min and max aggregates */
+				minmax_list = lappend(minmax_list, resname);
+				is_min_list = lappend_int(is_min_list, is_min);
+			}
 			else
 				elog(ERROR, "unsupported aggregate function: %s", aggname);
 		}
@@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 	if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0)
 	{
 		EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData));
+		SPITupleTable  *tuptable_recalc = NULL;
+		uint64			num_recalc;
 		int				rc;
 
 		/* convert tuplestores to ENR, and register for SPI */
@@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 			/* apply old delta and get rows to be recalculated */
 			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
 									   keys, aggs_list_buf, aggs_set_old,
-									   count_colname);
+									   minmax_list, is_min_list,
+									   count_colname, &tuptable_recalc, &num_recalc);
 		else
 			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
 
+		/*
+		 * If we have min or max, we might have to recalculate aggregate values from base tables
+		 * on some tuples. TIDs and keys such tuples are returned as a result of the above query.
+		 */
+		if (minmax_list && tuptable_recalc)
+			recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel);
+
 	}
 	/* For tuple insertion */
 	if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0)
@@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old,
 	);
 }
 
+/*
+ * append_set_clause_for_minmax
+ *
+ * Append SET clause string for min or max aggregation to given buffers.
+ * Also, append resnames required for calculating the aggregate value.
+ * is_min is true if this is min, false if not.
+ */
+static void
+append_set_clause_for_minmax(const char *resname, StringInfo buf_old,
+							 StringInfo buf_new, StringInfo aggs_list,
+							 bool is_min)
+{
+	char *count_col = IVM_colname("count", resname);
+
+	/* For tuple deletion */
+	if (buf_old)
+	{
+		/*
+		 * If the new value doesn't became NULL then use the value remaining
+		 * in the view although this will be recomputated afterwords.
+		 */
+		appendStringInfo(buf_old,
+			", %s = CASE WHEN %s THEN NULL ELSE %s END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_SUB, "mv", "t", count_col),
+			quote_qualified_identifier("mv", resname)
+		);
+		/* count = mv.count - t.count */
+		appendStringInfo(buf_old,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL)
+		);
+	}
+	/* For tuple insertion */
+	if (buf_new)
+	{
+		/*
+		 * min = LEAST(mv.min, diff.min)
+		 * max = GREATEST(mv.max, diff.max)
+		 */
+		appendStringInfo(buf_new,
+			", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END",
+			quote_qualified_identifier(NULL, resname),
+			get_null_condition_string(IVM_ADD, "mv", "diff", count_col),
+
+			is_min ? "LEAST" : "GREATEST",
+			quote_qualified_identifier("mv", resname),
+			quote_qualified_identifier("diff", resname)
+		);
+		/* count = mv.count + diff.count */
+		appendStringInfo(buf_new,
+			", %s = %s",
+			quote_qualified_identifier(NULL, count_col),
+			get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL)
+		);
+	}
+
+	appendStringInfo(aggs_list, ", %s, %s",
+		quote_qualified_identifier("diff", resname),
+		quote_qualified_identifier("diff", IVM_colname("count", resname))
+	);
+}
+
 /*
  * get_operation_string
  *
@@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2,
  * list to identify a tuple in the view. If the view has aggregates, this
  * requires strings representing resnames of aggregates and SET clause for
  * updating aggregate values.
+ *
+ * If the view has min or max aggregate, this requires a list of resnames of
+ * min/max aggregates and a list of boolean which represents which entries in
+ * minmax_list is min. These are necessary to check if we need to recalculate
+ * min or max aggregate values. In this case, this query returns TID and keys
+ * of tuples which need to be recalculated.  This result and the number of rows
+ * are stored in tuptables and num_recalc repectedly.
+ *
  */
 static void
 apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 				List *keys, StringInfo aggs_list, StringInfo aggs_set,
-				const char *count_colname)
+				List *minmax_list, List *is_min_list,
+				const char *count_colname,
+				SPITupleTable **tuptable_recalc, uint64 *num_recalc)
 {
 	StringInfoData	querybuf;
 	char   *match_cond;
+	char   *updt_returning = "";
+	char   *select_for_recalc = "SELECT";
 	bool	agg_without_groupby = (list_length(keys) == 0);
 
+	Assert(tuptable_recalc != NULL);
+	Assert(num_recalc != NULL);
+
 	/* build WHERE condition for searching tuples to be deleted */
 	match_cond = get_matching_condition_string(keys);
 
+	/*
+	 * We need a special RETURNING clause and SELECT statement for min/max to
+	 * check which tuple needs re-calculation from base tables.
+	 */
+	if (minmax_list)
+	{
+		updt_returning = get_returning_string(minmax_list, is_min_list, keys);
+		select_for_recalc = get_select_for_recalc_string(keys);
+	}
+
 	/* Search for matching tuples from the view and update or delete if found. */
 	initStringInfo(&querybuf);
 	appendStringInfo(&querybuf,
@@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
 											"%s"	/* SET clauses for aggregates */
 						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
-					")"
-					/* delete a tuple if this is to be deleted */
-					"DELETE FROM %s AS mv USING t "
-					"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt",
+						"%s"						/* RETURNING clause for recalc infomation */
+					"), dlt AS ("			/* delete a tuple if this is to be deleted */
+						"DELETE FROM %s AS mv USING t "
+						"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt"
+					") %s",							/* SELECT returning which tuples need to be recalculated */
 					count_colname,
 					count_colname, count_colname, (agg_without_groupby ? "false" : "true"),
 					(aggs_list != NULL ? aggs_list->data : ""),
@@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
 					match_cond,
 					matviewname, count_colname, count_colname, count_colname,
 					(aggs_set != NULL ? aggs_set->data : ""),
-					matviewname);
+					updt_returning,
+					matviewname,
+					select_for_recalc);
 
-	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT)
 		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+
+
+	/* Return tuples to be recalculated. */
+	if (minmax_list)
+	{
+		*tuptable_recalc = SPI_tuptable;
+		*num_recalc = SPI_processed;
+	}
+	else
+	{
+		*tuptable_recalc = NULL;
+		*num_recalc = 0;
+	}
 }
 
 /*
@@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys)
 	return match_cond.data;
 }
 
+/*
+ * get_returning_string
+ *
+ * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count.
+ * This clause returns ctid and a boolean value that indicates if we need to
+ * recalculate min or max value, for each updated row.
+ */
+static char *
+get_returning_string(List *minmax_list, List *is_min_list, List *keys)
+{
+	StringInfoData returning;
+	char		*recalc_cond;
+	ListCell	*lc;
+
+	Assert(minmax_list != NIL && is_min_list != NIL);
+	recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list);
+
+	initStringInfo(&returning);
+
+	appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond);
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		char *resname = NameStr(attr->attname);
+		appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname));
+	}
+
+	return returning.data;
+}
+
+/*
+ * get_minmax_recalc_condition_string
+ *
+ * Build a predicate string for checking if any min/max aggregate
+ * value needs to be recalculated.
+ */
+static char *
+get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list)
+{
+	StringInfoData recalc_cond;
+	ListCell	*lc1, *lc2;
+
+	initStringInfo(&recalc_cond);
+
+	Assert (list_length(minmax_list) == list_length(is_min_list));
+
+	forboth (lc1, minmax_list, lc2, is_min_list)
+	{
+		char   *resname = (char *) lfirst(lc1);
+		bool	is_min = (bool) lfirst_int(lc2);
+		char   *op_str = (is_min ? ">=" : "<=");
+
+		appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s",
+			quote_qualified_identifier("mv", resname),
+			op_str,
+			quote_qualified_identifier("t", resname)
+		);
+
+		if (lnext(minmax_list, lc1))
+			appendStringInfo(&recalc_cond, " OR ");
+	}
+
+	return recalc_cond.data;
+}
+
+/*
+ * get_select_for_recalc_string
+ *
+ * Build a query to return tid and keys of tuples which need
+ * recalculation. This is used as the result of the query
+ * built by apply_old_delta.
+ */
+static char *
+get_select_for_recalc_string(List *keys)
+{
+	StringInfoData qry;
+	ListCell	*lc;
+
+	initStringInfo(&qry);
+
+	appendStringInfo(&qry, "SELECT tid");
+	foreach (lc, keys)
+	{
+		Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+		appendStringInfo(&qry, ", %s", NameStr(attr->attname));
+	}
+
+	appendStringInfo(&qry, " FROM updt WHERE recalc");
+
+	return qry.data;
+}
+
+/*
+ * recalc_and_set_values
+ *
+ * Recalculate tuples in a materialized from base tables and update these.
+ * The tuples which needs recalculation are specified by keys, and resnames
+ * of columns to be updated are specified by namelist. TIDs and key values
+ * are given by tuples in tuptable_recalc. Its first attribute must be TID
+ * and key values must be following this.
+ */
+static void
+recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples,
+					  List *namelist, List *keys, Relation matviewRel)
+{
+	TupleDesc   tupdesc_recalc = tuptable_recalc->tupdesc;
+	Oid		   *keyTypes = NULL, *types = NULL;
+	char	   *keyNulls = NULL, *nulls = NULL;
+	Datum	   *keyVals = NULL, *vals = NULL;
+	int			num_vals = list_length(namelist);
+	int			num_keys = list_length(keys);
+	uint64      i;
+	Oid			matviewOid;
+	char	   *matviewname;
+
+	matviewOid = RelationGetRelid(matviewRel);
+	matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)),
+											 RelationGetRelationName(matviewRel));
+
+	/* If we have keys, initialize arrays for them. */
+	if (keys)
+	{
+		keyTypes = palloc(sizeof(Oid) * num_keys);
+		keyNulls = palloc(sizeof(char) * num_keys);
+		keyVals = palloc(sizeof(Datum) * num_keys);
+		/* a tuple contains keys to be recalculated and ctid to be updated*/
+		Assert(tupdesc_recalc->natts == num_keys + 1);
+
+		/* Types of key attributes  */
+		for (i = 0; i < num_keys; i++)
+			keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid;
+	}
+
+	/* allocate memory for all attribute names and tid */
+	types = palloc(sizeof(Oid) * (num_vals + 1));
+	nulls = palloc(sizeof(char) * (num_vals + 1));
+	vals = palloc(sizeof(Datum) * (num_vals + 1));
+
+	/* For each tuple which needs recalculation */
+	for (i = 0; i < num_tuples; i++)
+	{
+		int j;
+		bool isnull;
+		SPIPlanPtr plan;
+		SPITupleTable *tuptable_newvals;
+		TupleDesc   tupdesc_newvals;
+
+		/* Set group key values as parameters if needed. */
+		if (keys)
+		{
+			for (j = 0; j < num_keys; j++)
+			{
+				keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull);
+				if (isnull)
+					keyNulls[j] = 'n';
+				else
+					keyNulls[j] = ' ';
+			}
+		}
+
+		/*
+		 * Get recalculated values from base tables. The result must be
+		 * only one tuple thich contains the new values for specified keys.
+		 */
+		plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes);
+		if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT)
+			elog(ERROR, "SPI_execute_plan");
+		if (SPI_processed != 1)
+			elog(ERROR, "SPI_execute_plan returned zero or more than one rows");
+
+		tuptable_newvals = SPI_tuptable;
+		tupdesc_newvals = tuptable_newvals->tupdesc;
+
+		Assert(tupdesc_newvals->natts == num_vals);
+
+		/* Set the new values as parameters */
+		for (j = 0; j < tupdesc_newvals->natts; j++)
+		{
+			if (i == 0)
+				types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid;
+
+			vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull);
+			if (isnull)
+				nulls[j] = 'n';
+			else
+				nulls[j] = ' ';
+		}
+		/* Set TID of the view tuple to be updated as a parameter */
+		types[j] = TIDOID;
+		vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull);
+		nulls[j] = ' ';
+
+		/* Update the view tuple to the new values */
+		plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types);
+		if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE)
+			elog(ERROR, "SPI_execute_plan");
+	}
+}
+
+
+/*
+ * get_plan_for_recalc
+ *
+ * Create or fetch a plan for recalculating value in the view's target list
+ * from base tables using the definition query of materialized view specified
+ * by matviewOid. namelist is a list of resnames of values to be recalculated.
+ *
+ * keys is a list of keys to identify tuples to be recalculated if this is not
+ * empty. KeyTypes is an array of types of keys.
+ */
+static SPIPlanPtr
+get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes)
+{
+	MV_QueryKey hash_key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the recalculation */
+	mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC);
+	if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL)
+	{
+		ListCell	   *lc;
+		StringInfoData	str;
+		char   *viewdef;
+
+		/* get view definition of matview */
+		viewdef = text_to_cstring((text *) DatumGetPointer(
+					DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid))));
+		/* get rid of trailing semi-colon */
+		viewdef[strlen(viewdef)-1] = '\0';
+
+		/*
+		 * Build a query string for recalculating values. This is like
+		 *
+		 *  SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv
+		 *   WHERE (key1, key2, ...) = ($1, $2, ...);
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "SELECT ");
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, " FROM (%s) mv", viewdef);
+
+		if (keys)
+		{
+			int		i = 1;
+			char	paramname[16];
+
+			appendStringInfo(&str, " WHERE (");
+			foreach (lc, keys)
+			{
+				Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+				char   *resname = NameStr(attr->attname);
+				Oid		typid = attr->atttypid;
+
+				sprintf(paramname, "$%d", i);
+				appendStringInfo(&str, "(");
+				generate_equal(&str, typid, resname, paramname);
+				appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))",
+								 resname, paramname);
+
+				if (lnext(keys, lc))
+					appendStringInfoString(&str, " AND ");
+				i++;
+			}
+			appendStringInfo(&str, ")");
+		}
+		else
+			keyTypes = NULL;
+
+		plan = SPI_prepare(str.data, list_length(keys), keyTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&hash_key, plan);
+	}
+
+	return plan;
+}
+
+/*
+ * get_plan_for_set_values
+ *
+ * Create or fetch a plan for applying new values calculated by
+ * get_plan_for_recalc to a materialized view specified by matviewOid.
+ * matviewname is the name of the view.  namelist is a list of resnames
+ * of attributes to be updated, and valTypes is an array of types of the
+ * values.
+ */
+static SPIPlanPtr
+get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist,
+						Oid *valTypes)
+{
+	MV_QueryKey	key;
+	SPIPlanPtr	plan;
+
+	/* Fetch or prepare a saved plan for the real check */
+	mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE);
+	if ((plan = mv_FetchPreparedPlan(&key)) == NULL)
+	{
+		ListCell	  *lc;
+		StringInfoData str;
+		int		i;
+
+		/*
+		 * Build a query string for applying min/max values. This is like
+		 *
+		 *  UPDATE matviewname AS mv
+		 *   SET (x1, x2, x3, x4) = ($1, $2, $3, $4)
+		 *   WHERE ctid = $5;
+		 */
+
+		initStringInfo(&str);
+		appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname);
+		foreach (lc, namelist)
+		{
+			appendStringInfo(&str, "%s", (char *) lfirst(lc));
+			if (lnext(namelist, lc))
+				appendStringInfoString(&str, ", ");
+		}
+		appendStringInfo(&str, ") = ROW(");
+
+		for (i = 1; i <= list_length(namelist); i++)
+			appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i);
+
+		appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i);
+
+		plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes);
+		if (plan == NULL)
+			elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data);
+
+		SPI_keepplan(plan);
+		mv_HashPreparedPlan(&key, plan);
+	}
+
+	return plan;
+}
+
 /*
  * generate_equals
  *
@@ -3025,6 +3541,13 @@ mv_InitHashTables(void)
 {
 	HASHCTL		ctl;
 
+	memset(&ctl, 0, sizeof(ctl));
+	ctl.keysize = sizeof(MV_QueryKey);
+	ctl.entrysize = sizeof(MV_QueryHashEntry);
+	mv_query_cache = hash_create("MV query cache",
+								 MV_INIT_QUERYHASHSIZE,
+								 &ctl, HASH_ELEM | HASH_BLOBS);
+
 	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = sizeof(Oid);
 	ctl.entrysize = sizeof(MV_TriggerHashEntry);
@@ -3039,6 +3562,109 @@ mv_InitHashTables(void)
 							   &ctl, HASH_ELEM | HASH_BLOBS);
 }
 
+/*
+ * mv_FetchPreparedPlan
+ */
+static SPIPlanPtr
+mv_FetchPreparedPlan(MV_QueryKey *key)
+{
+	MV_QueryHashEntry *entry;
+	SPIPlanPtr	plan;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Lookup for the key
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_FIND, NULL);
+	if (entry == NULL)
+		return NULL;
+
+	/*
+	 * Check whether the plan is still valid.  If it isn't, we don't want to
+	 * simply rely on plancache.c to regenerate it; rather we should start
+	 * from scratch and rebuild the query text too.  This is to cover cases
+	 * such as table/column renames.  We depend on the plancache machinery to
+	 * detect possible invalidations, though.
+	 *
+	 * CAUTION: this check is only trustworthy if the caller has already
+	 * locked both materialized views and base tables.
+	 *
+	 * Also, check whether the search_path is still the same as when we made it.
+	 * If it isn't, we need to rebuild the query text because the result of
+	 * pg_ivm_get_viewdef() will change.
+	 */
+	plan = entry->plan;
+	if (plan && SPI_plan_is_valid(plan) &&
+		SearchPathMatchesCurrentEnvironment(entry->search_path))
+		return plan;
+
+	/*
+	 * Otherwise we might as well flush the cached plan now, to free a little
+	 * memory space before we make a new one.
+	 */
+	if (plan)
+		SPI_freeplan(plan);
+	if (entry->search_path)
+		pfree(entry->search_path);
+
+	entry->plan = NULL;
+	entry->search_path = NULL;
+
+	return NULL;
+}
+
+/*
+ * mv_HashPreparedPlan
+ *
+ * Add another plan to our private SPI query plan hashtable.
+ */
+static void
+mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan)
+{
+	MV_QueryHashEntry *entry;
+	bool		found;
+
+	/*
+	 * On the first call initialize the hashtable
+	 */
+	if (!mv_query_cache)
+		mv_InitHashTables();
+
+	/*
+	 * Add the new plan.  We might be overwriting an entry previously found
+	 * invalid by mv_FetchPreparedPlan.
+	 */
+	entry = (MV_QueryHashEntry *) hash_search(mv_query_cache,
+											  (void *) key,
+											  HASH_ENTER, &found);
+	Assert(!found || entry->plan == NULL);
+	entry->plan = plan;
+	entry->search_path = GetSearchPathMatcher(TopMemoryContext);
+}
+
+/*
+ * mv_BuildQueryKey
+ *
+ * Construct a hashtable key for a prepared SPI plan for IVM.
+ */
+static void
+mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type)
+{
+	/*
+	 * We assume struct MV_QueryKey contains no padding bytes, else we'd need
+	 * to use memset to clear them.
+	 */
+	key->matview_id = matview_id;
+	key->query_type = query_type;
+}
+
 /*
  * AtAbort_IVM
  *
-- 
2.43.0


--Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd
Content-Type: text/x-diff;
 name="v37-0008-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v37-0008-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 259+ messages in thread