Associate partitioning information with each RelOptInfo.

robertmhaas · robertmhaas · commit 9140cf8269b0 · 2017-09-20T23:39:13.000-04:00
This is not used for anything yet, but it is necessary infrastructure for partition-wise join and for partition pruning without constraint exclusion. Ashutosh Bapat, reviewed by Amit Langote and with quite a few changes, mostly cosmetic, by me. Additional review and testing of this patch series by Antonin Houska, Amit Khandekar, Rafia Sabih, Rajkumar Raghuwanshi, Thomas Munro, and Dilip Kumar. Discussion: http://postgr.es/m/CAFjFpRfneFG3H+F6BaiXemMrKF+FY-POpx3Ocy+RiH3yBmXSNw@mail.gmail.com
diff --git a/src/backend/optimizer/util/plancat.c b/src/backend/optimizer/util/plancat.c
@@ -68,6 +68,10 @@ static List *get_relation_constraints(PlannerInfo *root,
 static List *build_index_tlist(PlannerInfo *root, IndexOptInfo *index,
 				  Relation heapRelation);
 static List *get_relation_statistics(RelOptInfo *rel, Relation relation);
+static void set_relation_partition_info(PlannerInfo *root, RelOptInfo *rel,
+							Relation relation);
+static PartitionScheme find_partition_scheme(PlannerInfo *root, Relation rel);
+static List **build_baserel_partition_key_exprs(Relation relation, Index varno);
 
 /*
  * get_relation_info -
@@ -420,6 +424,13 @@ get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent,
 	/* Collect info about relation's foreign keys, if relevant */
 	get_relation_foreign_keys(root, rel, relation, inhparent);
 
+	/*
+	 * Collect info about relation's partitioning scheme, if any. Only
+	 * inheritance parents may be partitioned.
+	 */
+	if (inhparent && relation->rd_rel->relkind == RELKIND_PARTITIONED_TABLE)
+		set_relation_partition_info(root, rel, relation);
+
 	heap_close(relation, NoLock);
 
 	/*
@@ -1802,3 +1813,151 @@ has_row_triggers(PlannerInfo *root, Index rti, CmdType event)
 	heap_close(relation, NoLock);
 	return result;
 }
+
+/*
+ * set_relation_partition_info
+ *
+ * Set partitioning scheme and related information for a partitioned table.
+ */
+static void
+set_relation_partition_info(PlannerInfo *root, RelOptInfo *rel,
+							Relation relation)
+{
+	PartitionDesc partdesc;
+
+	Assert(relation->rd_rel->relkind == RELKIND_PARTITIONED_TABLE);
+
+	partdesc = RelationGetPartitionDesc(relation);
+	rel->part_scheme = find_partition_scheme(root, relation);
+	Assert(partdesc != NULL && rel->part_scheme != NULL);
+	rel->boundinfo = partdesc->boundinfo;
+	rel->nparts = partdesc->nparts;
+	rel->partexprs = build_baserel_partition_key_exprs(relation, rel->relid);
+}
+
+/*
+ * find_partition_scheme
+ *
+ * Find or create a PartitionScheme for this Relation.
+ */
+static PartitionScheme
+find_partition_scheme(PlannerInfo *root, Relation relation)
+{
+	PartitionKey partkey = RelationGetPartitionKey(relation);
+	ListCell   *lc;
+	int			partnatts;
+	PartitionScheme part_scheme;
+
+	/* A partitioned table should have a partition key. */
+	Assert(partkey != NULL);
+
+	partnatts = partkey->partnatts;
+
+	/* Search for a matching partition scheme and return if found one. */
+	foreach(lc, root->part_schemes)
+	{
+		part_scheme = lfirst(lc);
+
+		/* Match partitioning strategy and number of keys. */
+		if (partkey->strategy != part_scheme->strategy ||
+			partnatts != part_scheme->partnatts)
+			continue;
+
+		/* Match the partition key types. */
+		if (memcmp(partkey->partopfamily, part_scheme->partopfamily,
+				   sizeof(Oid) * partnatts) != 0 ||
+			memcmp(partkey->partopcintype, part_scheme->partopcintype,
+				   sizeof(Oid) * partnatts) != 0 ||
+			memcmp(partkey->parttypcoll, part_scheme->parttypcoll,
+				   sizeof(Oid) * partnatts) != 0)
+			continue;
+
+		/*
+		 * Length and byval information should match when partopcintype
+		 * matches.
+		 */
+		Assert(memcmp(partkey->parttyplen, part_scheme->parttyplen,
+					  sizeof(int16) * partnatts) == 0);
+		Assert(memcmp(partkey->parttypbyval, part_scheme->parttypbyval,
+					  sizeof(bool) * partnatts) == 0);
+
+		/* Found matching partition scheme. */
+		return part_scheme;
+	}
+
+	/*
+	 * Did not find matching partition scheme. Create one copying relevant
+	 * information from the relcache. Instead of copying whole arrays, copy
+	 * the pointers in relcache. It's safe to do so since
+	 * RelationClearRelation() wouldn't change it while planner is using it.
+	 */
+	part_scheme = (PartitionScheme) palloc0(sizeof(PartitionSchemeData));
+	part_scheme->strategy = partkey->strategy;
+	part_scheme->partnatts = partkey->partnatts;
+	part_scheme->partopfamily = partkey->partopfamily;
+	part_scheme->partopcintype = partkey->partopcintype;
+	part_scheme->parttypcoll = partkey->parttypcoll;
+	part_scheme->parttyplen = partkey->parttyplen;
+	part_scheme->parttypbyval = partkey->parttypbyval;
+
+	/* Add the partitioning scheme to PlannerInfo. */
+	root->part_schemes = lappend(root->part_schemes, part_scheme);
+
+	return part_scheme;
+}
+
+/*
+ * build_baserel_partition_key_exprs
+ *
+ * Collects partition key expressions for a given base relation.  Any single
+ * column partition keys are converted to Var nodes.  All Var nodes are set
+ * to the given varno.  The partition key expressions are returned as an array
+ * of single element lists to be stored in RelOptInfo of the base relation.
+ */
+static List **
+build_baserel_partition_key_exprs(Relation relation, Index varno)
+{
+	PartitionKey partkey = RelationGetPartitionKey(relation);
+	int			partnatts;
+	int			cnt;
+	List	  **partexprs;
+	ListCell   *lc;
+
+	/* A partitioned table should have a partition key. */
+	Assert(partkey != NULL);
+
+	partnatts = partkey->partnatts;
+	partexprs = (List **) palloc(sizeof(List *) * partnatts);
+	lc = list_head(partkey->partexprs);
+
+	for (cnt = 0; cnt < partnatts; cnt++)
+	{
+		Expr	   *partexpr;
+		AttrNumber	attno = partkey->partattrs[cnt];
+
+		if (attno != InvalidAttrNumber)
+		{
+			/* Single column partition key is stored as a Var node. */
+			Assert(attno > 0);
+
+			partexpr = (Expr *) makeVar(varno, attno,
+										partkey->parttypid[cnt],
+										partkey->parttypmod[cnt],
+										partkey->parttypcoll[cnt], 0);
+		}
+		else
+		{
+			if (lc == NULL)
+				elog(ERROR, "wrong number of partition key expressions");
+
+			/* Re-stamp the expression with given varno. */
+			partexpr = (Expr *) copyObject(lfirst(lc));
+			ChangeVarNodes((Node *) partexpr, 1, varno, 0);
+			lc = lnext(lc);
+		}
+
+		partexprs[cnt] = list_make1(partexpr);
+	}
+
+	return partexprs;
+}
diff --git a/src/backend/optimizer/util/relnode.c b/src/backend/optimizer/util/relnode.c
@@ -146,6 +146,11 @@ build_simple_rel(PlannerInfo *root, int relid, RelOptInfo *parent)
 	rel->baserestrict_min_security = UINT_MAX;
 	rel->joininfo = NIL;
 	rel->has_eclass_joins = false;
+	rel->part_scheme = NULL;
+	rel->nparts = 0;
+	rel->boundinfo = NULL;
+	rel->part_rels = NULL;
+	rel->partexprs = NULL;
 
 	/*
 	 * Pass top parent's relids down the inheritance hierarchy. If the parent
@@ -218,18 +223,41 @@ build_simple_rel(PlannerInfo *root, int relid, RelOptInfo *parent)
 	if (rte->inh)
 	{
 		ListCell   *l;
+		int			nparts = rel->nparts;
+		int			cnt_parts = 0;
+
+		if (nparts > 0)
+			rel->part_rels = (RelOptInfo **)
+				palloc(sizeof(RelOptInfo *) * nparts);
 
 		foreach(l, root->append_rel_list)
 		{
 			AppendRelInfo *appinfo = (AppendRelInfo *) lfirst(l);
+			RelOptInfo *childrel;
 
 			/* append_rel_list contains all append rels; ignore others */
 			if (appinfo->parent_relid != relid)
 				continue;
 
-			(void) build_simple_rel(root, appinfo->child_relid,
-									rel);
+			childrel = build_simple_rel(root, appinfo->child_relid,
+										rel);
+
+			/* Nothing more to do for an unpartitioned table. */
+			if (!rel->part_scheme)
+				continue;
+
+			/*
+			 * The order of partition OIDs in append_rel_list is the same as
+			 * the order in the PartitionDesc, so the order of part_rels will
+			 * also match the PartitionDesc.  See expand_partitioned_rtentry.
+			 */
+			Assert(cnt_parts < nparts);
+			rel->part_rels[cnt_parts] = childrel;
+			cnt_parts++;
 		}
+
+		/* We should have seen all the child partitions. */
+		Assert(cnt_parts == nparts);
 	}
 
 	return rel;
@@ -527,6 +555,11 @@ build_join_rel(PlannerInfo *root,
 	joinrel->joininfo = NIL;
 	joinrel->has_eclass_joins = false;
 	joinrel->top_parent_relids = NULL;
+	joinrel->part_scheme = NULL;
+	joinrel->nparts = 0;
+	joinrel->boundinfo = NULL;
+	joinrel->part_rels = NULL;
+	joinrel->partexprs = NULL;
 
 	/* Compute information relevant to the foreign relations. */
 	set_foreign_rel_properties(joinrel, outer_rel, inner_rel);
diff --git a/src/include/nodes/relation.h b/src/include/nodes/relation.h
@@ -266,6 +266,9 @@ typedef struct PlannerInfo
 	List	   *distinct_pathkeys;	/* distinctClause pathkeys, if any */
 	List	   *sort_pathkeys;	/* sortClause pathkeys, if any */
 
+	List	   *part_schemes;	/* Canonicalised partition schemes used in the
+								 * query. */
+
 	List	   *initial_rels;	/* RelOptInfos we are now trying to join */
 
 	/* Use fetch_upper_rel() to get any particular upper rel */
@@ -326,6 +329,34 @@ typedef struct PlannerInfo
 	((root)->simple_rte_array ? (root)->simple_rte_array[rti] : \
 	 rt_fetch(rti, (root)->parse->rtable))
 
+/*
+ * If multiple relations are partitioned the same way, all such partitions
+ * will have a pointer to the same PartitionScheme.  A list of PartitionScheme
+ * objects is attached to the PlannerInfo.  By design, the partition scheme
+ * incorporates only the general properties of the partition method (LIST vs.
+ * RANGE, number of partitioning columns and the type information for each)
+ * and not the specific bounds.
+ *
+ * We store the opclass-declared input data types instead of the partition key
+ * datatypes since the former rather than the latter are used to compare
+ * partition bounds. Since partition key data types and the opclass declared
+ * input data types are expected to be binary compatible (per ResolveOpClass),
+ * both of those should have same byval and length properties.
+ */
+typedef struct PartitionSchemeData
+{
+	char		strategy;		/* partition strategy */
+	int16		partnatts;		/* number of partition attributes */
+	Oid		   *partopfamily;	/* OIDs of operator families */
+	Oid		   *partopcintype;	/* OIDs of opclass declared input data types */
+	Oid		   *parttypcoll;	/* OIDs of collations of partition keys. */
+
+	/* Cached information about partition key data types. */
+	int16	   *parttyplen;
+	bool	   *parttypbyval;
+}			PartitionSchemeData;
+
+typedef struct PartitionSchemeData *PartitionScheme;
 
 /*----------
  * RelOptInfo
@@ -456,7 +487,7 @@ typedef struct PlannerInfo
  *					other rels for which we have tried and failed to prove
  *					this one unique
  *
- * The presence of the remaining fields depends on the restrictions
+ * The presence of the following fields depends on the restrictions
  * and joins that the relation participates in:
  *
  *		baserestrictinfo - List of RestrictInfo nodes, containing info about
@@ -487,6 +518,21 @@ typedef struct PlannerInfo
  * We store baserestrictcost in the RelOptInfo (for base relations) because
  * we know we will need it at least once (to price the sequential scan)
  * and may need it multiple times to price index scans.
+ *
+ * If the relation is partitioned, these fields will be set:
+ *
+ * 		part_scheme - Partitioning scheme of the relation
+ * 		boundinfo - Partition bounds
+ * 		nparts - Number of partitions
+ * 		part_rels - RelOptInfos for each partition
+ * 		partexprs - Partition key expressions
+ *
+ * Note: A base relation always has only one set of partition keys, but a join
+ * relation may have as many sets of partition keys as the number of relations
+ * being joined. partexprs is an array containing part_scheme->partnatts
+ * elements, each of which is a list of partition key expressions. For a base
+ * relation each list contains only one expression, but for a join relation
+ * there can be one per baserel.
  *----------
  */
 typedef enum RelOptKind
@@ -592,6 +638,14 @@ typedef struct RelOptInfo
 
 	/* used by "other" relations */
 	Relids		top_parent_relids;	/* Relids of topmost parents */
+
+	/* used for partitioned relations */
+	PartitionScheme part_scheme;	/* Partitioning scheme. */
+	int			nparts;			/* number of partitions */
+	struct PartitionBoundInfoData *boundinfo;	/* Partition bounds */
+	struct RelOptInfo **part_rels;	/* Array of RelOptInfos of partitions,
+									 * stored in the same order of bounds */
+	List	  **partexprs;		/* Partition key expressions. */
 } RelOptInfo;
 
 /*
