agora inbox for [email protected]  
help / color / mirror / Atom feed
[PATCH 3/5] Force GIN recheck for empty ALL keys more accurately
2+ messages / 2 participants
[nested] [flat]

* [PATCH 3/5] Force GIN recheck for empty ALL keys more accurately
@ 2019-11-22 00:24  Nikita Glukhov <[email protected]>
  0 siblings, 0 replies; 2+ messages in thread

From: Nikita Glukhov @ 2019-11-22 00:24 UTC (permalink / raw)

---
 src/backend/access/gin/ginscan.c | 81 +++++++++++++++++++++++++++++++---------
 1 file changed, 64 insertions(+), 17 deletions(-)

diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index 903891f..47beef3 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -129,19 +129,21 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
  * Initialize the next GinScanKey using the output from the extractQueryFn
  */
 static void
-ginFillScanKey(GinScanOpaque so, OffsetNumber attnum,
-			   StrategyNumber strategy, int32 searchMode,
+ginFillScanKey(GinScanOpaque so, GinScanKey	key, bool initHiddenEntries,
+			   OffsetNumber attnum, StrategyNumber strategy, int32 searchMode,
 			   Datum query, uint32 nQueryValues,
 			   Datum *queryValues, GinNullCategory *queryCategories,
 			   bool *partial_matches, Pointer *extra_data)
 {
-	GinScanKey	key = &(so->keys[so->nkeys++]);
 	GinState   *ginstate = &so->ginstate;
 	uint32		nUserQueryValues = nQueryValues;
 	uint32		i;
 
+	if (key == NULL)
+		key = &(so->keys[so->nkeys++]);
+
 	/* Non-default search modes add one "hidden" entry to each key */
-	if (searchMode != GIN_SEARCH_MODE_DEFAULT)
+	if (searchMode != GIN_SEARCH_MODE_DEFAULT && initHiddenEntries)
 		nQueryValues++;
 	key->nentries = nQueryValues;
 	key->nuserentries = nUserQueryValues;
@@ -270,8 +272,14 @@ ginNewScanKey(IndexScanDesc scan)
 	GinScanOpaque so = (GinScanOpaque) scan->opaque;
 	int			i;
 	bool		hasNullQuery = false;
-	bool		colNotNull[INDEX_MAX_KEYS] = {0};
-	int			numNotNullKeys = 0;
+	/*
+	 * GIN_FALSE - column has no search keys
+	 * GIN_TRUE  - NOT NULL is implied by some non-empty search key
+	 * GIN_MAYBE - NOT NULL is implied by some empty ALL key
+	 */
+	GinTernaryValue	colNotNull[INDEX_MAX_KEYS] = {0};
+	/* Number of GIN_MAYBE values in colNotNull[]  */
+	int			colNotNullCount = 0;
 	MemoryContext oldCtx;
 
 	/*
@@ -360,13 +368,34 @@ ginNewScanKey(IndexScanDesc scan)
 				 * any non-ALL scankeys; otherwise we end up adding a NOT_NULL
 				 * scankey below.
 				 */
-				so->forcedRecheck = true;
+				GinScanKeyData key;
+				GinTernaryValue res;
+
+				/* Check whether unconditional recheck is needed. */
+				ginFillScanKey(so, &key, false, skey->sk_attno,
+							   skey->sk_strategy, searchMode,
+							   skey->sk_argument, 0,
+							   NULL, NULL, NULL, NULL);
+
+				res = key.triConsistentFn(&key);
+
+				if (res == GIN_FALSE)
+				{
+					so->isVoidRes = true;	/* unsatisfiable query */
+					break;
+				}
+
+				so->forcedRecheck |= res != GIN_TRUE;
 
 				/*
-				 * Increment the number of columns with NOT NULL constraints.
+				 * Increment the number of columns with NOT NULL constraints
+				 * if NOT NULL is not yet implied by some non-empty key.
 				 */
-				colNotNull[colno] = true;
-				numNotNullKeys++;
+				if (colNotNull[colno] == GIN_FALSE)
+				{
+					colNotNull[colno] = GIN_MAYBE;
+					colNotNullCount++;
+				}
 
 				continue;
 			}
@@ -375,6 +404,16 @@ ginNewScanKey(IndexScanDesc scan)
 		}
 
 		/*
+		 * Current non-empty key implies that column is NOT NULL, so decrement
+		 * the number of columns with NOT NULL if NOT NULL already is implied by
+		 * some empty ALL key.
+		 */
+		if (colNotNull[colno] == GIN_MAYBE)
+			colNotNullCount--;
+
+		colNotNull[colno] = GIN_TRUE;
+
+		/*
 		 * Create GinNullCategory representation.  If the extractQueryFn
 		 * didn't create a nullFlags array, we assume everything is non-null.
 		 * While at it, detect whether any null keys are present.
@@ -394,7 +433,7 @@ ginNewScanKey(IndexScanDesc scan)
 			}
 		}
 
-		ginFillScanKey(so, skey->sk_attno,
+		ginFillScanKey(so, NULL, true, skey->sk_attno,
 					   skey->sk_strategy, searchMode,
 					   skey->sk_argument, nQueryValues,
 					   queryValues, categories,
@@ -412,24 +451,32 @@ ginNewScanKey(IndexScanDesc scan)
 			hasNullQuery = true;
 
 			/* Initialize EVERYTHING key if there are no non-NULL columns. */
-			if (!numNotNullKeys)
+			if (!colNotNullCount)
 			{
-				ginFillScanKey(so, FirstOffsetNumber, InvalidStrategy,
-							   GIN_SEARCH_MODE_EVERYTHING, (Datum) 0, 0,
-							   NULL, NULL, NULL, NULL);
+				ginFillScanKey(so, NULL, true, FirstOffsetNumber,
+							   InvalidStrategy, GIN_SEARCH_MODE_EVERYTHING,
+							   (Datum) 0, 0, NULL, NULL, NULL, NULL);
 			}
 			else
 			{
 				/* Initialize NOT_NULL key for each non-NULL column. */
 				for (i = 0; i < scan->indexRelation->rd_att->natts; i++)
 				{
-					if (colNotNull[i])
-						ginFillScanKey(so, i + 1, InvalidStrategy,
+					if (colNotNull[i] == GIN_MAYBE)
+						ginFillScanKey(so, NULL, true, i + 1, InvalidStrategy,
 									   GIN_SEARCH_MODE_NOT_NULL, (Datum) 0, 0,
 									   NULL, NULL, NULL, NULL);
 				}
 			}
 		}
+		else if (colNotNullCount)
+		{
+			/*
+			 * We use recheck instead of adding NOT_NULL entries to eliminate
+			 * rows with NULL columns.
+			 */
+			so->forcedRecheck = true;
+		}
 
 		/*
 		 * If the index is version 0, it may be missing null and placeholder
-- 
2.7.4


--------------C5A6759166AE2CA1CB41B4D8
Content-Type: text/x-patch;
 name="0004-Avoid-GIN-full-scan-for-non-empty-ALL-keys-v08.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename*0="0004-Avoid-GIN-full-scan-for-non-empty-ALL-keys-v08.patch"



^ permalink  raw  reply  [nested|flat] 2+ messages in thread

* [PATCH 2/5] Refactor index_concurrently_create_copy() for use with REPACK (CONCURRENTLY).
@ 2026-02-16 19:49  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 2+ messages in thread

From: Antonin Houska @ 2026-02-16 19:49 UTC (permalink / raw)

This patch moves the code to index_create_copy() and adds a "concurrently"
parameter so it can be used by REPACK (CONCURRENTLY).

With the CONCURRENTLY option, REPACK cannot simply swap the heap file and
rebuild its indexes. Instead, it needs to build a separate set of indexes
(including system catalog entries) *before* the actual swap, to reduce the
time AccessExclusiveLock needs to be held for.
---
 src/backend/catalog/index.c      | 54 +++++++++++++++++++++++---------
 src/backend/commands/indexcmds.c |  6 ++--
 src/backend/nodes/makefuncs.c    |  9 +++---
 src/include/catalog/index.h      |  3 ++
 src/include/nodes/makefuncs.h    |  4 ++-
 5 files changed, 54 insertions(+), 22 deletions(-)

diff --git a/src/backend/catalog/index.c b/src/backend/catalog/index.c
index 5ee6389d39c..f8e6c3d804e 100644
--- a/src/backend/catalog/index.c
+++ b/src/backend/catalog/index.c
@@ -1288,15 +1288,32 @@ index_create(Relation heapRelation,
 /*
  * index_concurrently_create_copy
  *
- * Create concurrently an index based on the definition of the one provided by
- * caller.  The index is inserted into catalogs and needs to be built later
- * on.  This is called during concurrent reindex processing.
- *
- * "tablespaceOid" is the tablespace to use for this index.
+ * Variant of index_create_copy(), called during concurrent reindex
+ * processing.
  */
 Oid
 index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
 							   Oid tablespaceOid, const char *newName)
+{
+	return index_create_copy(heapRelation, oldIndexId, tablespaceOid, newName,
+							 true);
+}
+
+/*
+ * index_create_copy
+ *
+ * Create an index based on the definition of the one provided by caller.  The
+ * index is inserted into catalogs. If 'concurrently' is TRUE, it needs to be
+ * built later on, otherwise it's built immediately.
+ *
+ * "tablespaceOid" is the tablespace to use for this index.
+ *
+ * The actual implementation of index_concurrently_create_copy(), reusable for
+ * other purposes.
+ */
+Oid
+index_create_copy(Relation heapRelation, Oid oldIndexId, Oid tablespaceOid,
+				  const char *newName, bool concurrently)
 {
 	Relation	indexRelation;
 	IndexInfo  *oldInfo,
@@ -1315,6 +1332,7 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
 	List	   *indexColNames = NIL;
 	List	   *indexExprs = NIL;
 	List	   *indexPreds = NIL;
+	int			flags = 0;
 
 	indexRelation = index_open(oldIndexId, RowExclusiveLock);
 
@@ -1325,7 +1343,7 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
 	 * Concurrent build of an index with exclusion constraints is not
 	 * supported.
 	 */
-	if (oldInfo->ii_ExclusionOps != NULL)
+	if (oldInfo->ii_ExclusionOps != NULL && concurrently)
 		ereport(ERROR,
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 				 errmsg("concurrent index creation for exclusion constraints is not supported")));
@@ -1381,9 +1399,7 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
 	}
 
 	/*
-	 * Build the index information for the new index.  Note that rebuild of
-	 * indexes with exclusion constraints is not supported, hence there is no
-	 * need to fill all the ii_Exclusion* fields.
+	 * Build the index information for the new index.
 	 */
 	newInfo = makeIndexInfo(oldInfo->ii_NumIndexAttrs,
 							oldInfo->ii_NumIndexKeyAttrs,
@@ -1392,10 +1408,13 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
 							indexPreds,
 							oldInfo->ii_Unique,
 							oldInfo->ii_NullsNotDistinct,
-							false,	/* not ready for inserts */
-							true,
+							!concurrently,	/* isready */
+							concurrently,	/* concurrent */
 							indexRelation->rd_indam->amsummarizing,
-							oldInfo->ii_WithoutOverlaps);
+							oldInfo->ii_WithoutOverlaps,
+							oldInfo->ii_ExclusionOps,
+							oldInfo->ii_ExclusionProcs,
+							oldInfo->ii_ExclusionStrats);
 
 	/*
 	 * Extract the list of column names and the column numbers for the new
@@ -1433,6 +1452,9 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
 		stattargets[i].isnull = isnull;
 	}
 
+	if (concurrently)
+		flags = INDEX_CREATE_SKIP_BUILD | INDEX_CREATE_CONCURRENT;
+
 	/*
 	 * Now create the new index.
 	 *
@@ -1456,7 +1478,7 @@ index_concurrently_create_copy(Relation heapRelation, Oid oldIndexId,
 							  indcoloptions->values,
 							  stattargets,
 							  reloptionsDatum,
-							  INDEX_CREATE_SKIP_BUILD | INDEX_CREATE_CONCURRENT,
+							  flags,
 							  0,
 							  true, /* allow table to be a system catalog? */
 							  false,	/* is_internal? */
@@ -2450,7 +2472,8 @@ BuildIndexInfo(Relation index)
 					   indexStruct->indisready,
 					   false,
 					   index->rd_indam->amsummarizing,
-					   indexStruct->indisexclusion && indexStruct->indisunique);
+					   indexStruct->indisexclusion && indexStruct->indisunique,
+					   NULL, NULL, NULL);
 
 	/* fill in attribute numbers */
 	for (i = 0; i < numAtts; i++)
@@ -2510,7 +2533,8 @@ BuildDummyIndexInfo(Relation index)
 					   indexStruct->indisready,
 					   false,
 					   index->rd_indam->amsummarizing,
-					   indexStruct->indisexclusion && indexStruct->indisunique);
+					   indexStruct->indisexclusion && indexStruct->indisunique,
+					   NULL, NULL, NULL);
 
 	/* fill in attribute numbers */
 	for (i = 0; i < numAtts; i++)
diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c
index 635679cc1f2..34209bd1393 100644
--- a/src/backend/commands/indexcmds.c
+++ b/src/backend/commands/indexcmds.c
@@ -243,7 +243,8 @@ CheckIndexCompatible(Oid oldId,
 	 */
 	indexInfo = makeIndexInfo(numberOfAttributes, numberOfAttributes,
 							  accessMethodId, NIL, NIL, false, false,
-							  false, false, amsummarizing, isWithoutOverlaps);
+							  false, false, amsummarizing, isWithoutOverlaps,
+							  NULL, NULL, NULL);
 	typeIds = palloc_array(Oid, numberOfAttributes);
 	collationIds = palloc_array(Oid, numberOfAttributes);
 	opclassIds = palloc_array(Oid, numberOfAttributes);
@@ -930,7 +931,8 @@ DefineIndex(ParseState *pstate,
 							  !concurrent,
 							  concurrent,
 							  amissummarizing,
-							  stmt->iswithoutoverlaps);
+							  stmt->iswithoutoverlaps,
+							  NULL, NULL, NULL);
 
 	typeIds = palloc_array(Oid, numberOfAttributes);
 	collationIds = palloc_array(Oid, numberOfAttributes);
diff --git a/src/backend/nodes/makefuncs.c b/src/backend/nodes/makefuncs.c
index 2caec621d73..ca7e21e8349 100644
--- a/src/backend/nodes/makefuncs.c
+++ b/src/backend/nodes/makefuncs.c
@@ -834,7 +834,8 @@ IndexInfo *
 makeIndexInfo(int numattrs, int numkeyattrs, Oid amoid, List *expressions,
 			  List *predicates, bool unique, bool nulls_not_distinct,
 			  bool isready, bool concurrent, bool summarizing,
-			  bool withoutoverlaps)
+			  bool withoutoverlaps, Oid *exclusion_ops, Oid *exclusion_procs,
+			  uint16 *exclusion_strats)
 {
 	IndexInfo  *n = makeNode(IndexInfo);
 
@@ -863,9 +864,9 @@ makeIndexInfo(int numattrs, int numkeyattrs, Oid amoid, List *expressions,
 	n->ii_PredicateState = NULL;
 
 	/* exclusion constraints */
-	n->ii_ExclusionOps = NULL;
-	n->ii_ExclusionProcs = NULL;
-	n->ii_ExclusionStrats = NULL;
+	n->ii_ExclusionOps = exclusion_ops;
+	n->ii_ExclusionProcs = exclusion_procs;
+	n->ii_ExclusionStrats = exclusion_strats;
 
 	/* speculative inserts */
 	n->ii_UniqueOps = NULL;
diff --git a/src/include/catalog/index.h b/src/include/catalog/index.h
index b259c4141ed..3426087b445 100644
--- a/src/include/catalog/index.h
+++ b/src/include/catalog/index.h
@@ -99,6 +99,9 @@ extern Oid	index_concurrently_create_copy(Relation heapRelation,
 										   Oid oldIndexId,
 										   Oid tablespaceOid,
 										   const char *newName);
+extern Oid	index_create_copy(Relation heapRelation, Oid oldIndexId,
+							  Oid tablespaceOid, const char *newName,
+							  bool concurrently);
 
 extern void index_concurrently_build(Oid heapRelationId,
 									 Oid indexRelationId);
diff --git a/src/include/nodes/makefuncs.h b/src/include/nodes/makefuncs.h
index 982ec25ae14..dcea148ae1a 100644
--- a/src/include/nodes/makefuncs.h
+++ b/src/include/nodes/makefuncs.h
@@ -99,7 +99,9 @@ extern IndexInfo *makeIndexInfo(int numattrs, int numkeyattrs, Oid amoid,
 								List *expressions, List *predicates,
 								bool unique, bool nulls_not_distinct,
 								bool isready, bool concurrent,
-								bool summarizing, bool withoutoverlaps);
+								bool summarizing, bool withoutoverlaps,
+								Oid *exclusion_ops, Oid *exclusion_procs,
+								uint16 *exclusion_strats);
 
 extern Node *makeStringConst(char *str, int location);
 extern DefElem *makeDefElem(char *name, Node *arg, int location);
-- 
2.47.3


--=-=-=
Content-Type: text/x-diff
Content-Disposition: attachment;
 filename=v34-0003-Move-conversion-of-a-historic-to-MVCC-snapshot-to-a-.patch



^ permalink  raw  reply  [nested|flat] 2+ messages in thread


end of thread, other threads:[~2026-02-16 19:49 UTC | newest]

Thread overview: 2+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2019-11-22 00:24 [PATCH 3/5] Force GIN recheck for empty ALL keys more accurately Nikita Glukhov <[email protected]>
2026-02-16 19:49 [PATCH 2/5] Refactor index_concurrently_create_copy() for use with REPACK (CONCURRENTLY). Antonin Houska <[email protected]>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox