Add a 'parallel_degree' reloption.

robertmhaas · robertmhaas · commit 25fe8b5f1ac9 · 2016-04-08T11:14:56.000-04:00
The code that estimates what parallel degree should be uesd for the
scan of a relation is currently rather stupid, so add a parallel_degree
reloption that can be used to override the planner's rather limited
judgement.

Julien Rouhaud, reviewed by David Rowley, James Sewell, Amit Kapila,
and me.  Some further hacking by me.
diff --git a/doc/src/sgml/ref/create_table.sgml b/doc/src/sgml/ref/create_table.sgml
@@ -908,6 +908,19 @@ CREATE [ [ GLOBAL | LOCAL ] { TEMPORARY | TEMP } | UNLOGGED ] TABLE [ IF NOT EXI
     </listitem>
    </varlistentry>
 
+   <varlistentry>
+    <term><literal>parallel_degree</> (<type>integer</>)</term>
+    <listitem>
+     <para>
+      The parallel degree for a table is the number of workers that should
+      be used to assist a parallel scan of that table.  If not set, the
+      system will determine a value based on the relation size.  The actual
+      number of workers chosen by the planner may be less, for example due to
+      the setting of <xref linkend="guc-max-parallel-degree">.
+     </para>
+    </listitem>
+   </varlistentry>
+
    <varlistentry>
     <term><literal>autovacuum_enabled</>, <literal>toast.autovacuum_enabled</literal> (<type>boolean</>)</term>
     <listitem>
diff --git a/src/backend/access/common/reloptions.c b/src/backend/access/common/reloptions.c
@@ -26,6 +26,7 @@
 #include "commands/tablespace.h"
 #include "commands/view.h"
 #include "nodes/makefuncs.h"
+#include "postmaster/postmaster.h"
 #include "utils/array.h"
 #include "utils/attoptcache.h"
 #include "utils/builtins.h"
@@ -267,6 +268,15 @@ static relopt_int intRelOpts[] =
 		0, 0, 0
 #endif
 	},
+	{
+		{
+			"parallel_degree",
+			"Number of parallel processes that can be used per executor node for this relation.",
+			RELOPT_KIND_HEAP,
+			AccessExclusiveLock
+		},
+		-1, 0, MAX_BACKENDS
+	},
 
 	/* list terminator */
 	{{NULL}}
@@ -1251,8 +1261,7 @@ fillRelOptions(void *rdopts, Size basesize,
 
 
 /*
- * Option parser for anything that uses StdRdOptions (i.e. fillfactor and
- * autovacuum)
+ * Option parser for anything that uses StdRdOptions.
  */
 bytea *
 default_reloptions(Datum reloptions, bool validate, relopt_kind kind)
@@ -1291,7 +1300,9 @@ default_reloptions(Datum reloptions, bool validate, relopt_kind kind)
 		{"autovacuum_analyze_scale_factor", RELOPT_TYPE_REAL,
 		offsetof(StdRdOptions, autovacuum) +offsetof(AutoVacOpts, analyze_scale_factor)},
 		{"user_catalog_table", RELOPT_TYPE_BOOL,
-		offsetof(StdRdOptions, user_catalog_table)}
+		offsetof(StdRdOptions, user_catalog_table)},
+		{"parallel_degree", RELOPT_TYPE_INT,
+		offsetof(StdRdOptions, parallel_degree)}
 	};
 
 	options = parseRelOptions(reloptions, validate, kind, &numoptions);
diff --git a/src/backend/optimizer/path/allpaths.c b/src/backend/optimizer/path/allpaths.c
@@ -659,31 +659,55 @@ set_plain_rel_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
 static void
 create_parallel_paths(PlannerInfo *root, RelOptInfo *rel)
 {
-	int		parallel_threshold = 1000;
-	int		parallel_degree = 1;
+	int			parallel_degree = 1;
 
 	/*
-	 * If this relation is too small to be worth a parallel scan, just return
-	 * without doing anything ... unless it's an inheritance child.  In that case,
-	 * we want to generate a parallel path here anyway.  It might not be worthwhile
-	 * just for this relation, but when combined with all of its inheritance siblings
-	 * it may well pay off.
+	 * If the user has set the parallel_degree reloption, we decide what to do
+	 * based on the value of that option.  Otherwise, we estimate a value.
 	 */
-	if (rel->pages < parallel_threshold && rel->reloptkind == RELOPT_BASEREL)
-		return;
+	if (rel->rel_parallel_degree != -1)
+	{
+		/*
+		 * If parallel_degree = 0 is set for this relation, bail out.  The
+		 * user does not want a parallel path for this relation.
+		 */
+		if (rel->rel_parallel_degree == 0)
+			return;
 
-	/*
-	 * Limit the degree of parallelism logarithmically based on the size of the
-	 * relation.  This probably needs to be a good deal more sophisticated, but we
-	 * need something here for now.
-	 */
-	while (rel->pages > parallel_threshold * 3 &&
-		   parallel_degree < max_parallel_degree)
+		/*
+		 * Use the table parallel_degree, but don't go further than
+		 * max_parallel_degree.
+		 */
+		parallel_degree = Min(rel->rel_parallel_degree, max_parallel_degree);
+	}
+	else
 	{
-		parallel_degree++;
-		parallel_threshold *= 3;
-		if (parallel_threshold >= PG_INT32_MAX / 3)
-			break;
+		int			parallel_threshold = 1000;
+
+		/*
+		 * If this relation is too small to be worth a parallel scan, just
+		 * return without doing anything ... unless it's an inheritance child.
+		 * In that case, we want to generate a parallel path here anyway.  It
+		 * might not be worthwhile just for this relation, but when combined
+		 * with all of its inheritance siblings it may well pay off.
+		 */
+		if (rel->pages < parallel_threshold &&
+			rel->reloptkind == RELOPT_BASEREL)
+			return;
+
+		/*
+		 * Limit the degree of parallelism logarithmically based on the size
+		 * of the relation.  This probably needs to be a good deal more
+		 * sophisticated, but we need something here for now.
+		 */
+		while (rel->pages > parallel_threshold * 3 &&
+			   parallel_degree < max_parallel_degree)
+		{
+			parallel_degree++;
+			parallel_threshold *= 3;
+			if (parallel_threshold >= PG_INT32_MAX / 3)
+				break;
+		}
 	}
 
 	/* Add an unordered partial path based on a parallel sequential scan. */
diff --git a/src/backend/optimizer/util/plancat.c b/src/backend/optimizer/util/plancat.c
@@ -133,6 +133,9 @@ get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent,
 		estimate_rel_size(relation, rel->attr_widths - rel->min_attr,
 						  &rel->pages, &rel->tuples, &rel->allvisfrac);
 
+	/* Retrive the parallel_degree reloption, if set. */
+	rel->rel_parallel_degree = RelationGetParallelDegree(relation, -1);
+
 	/*
 	 * Make list of indexes.  Ignore indexes on system catalogs if told to.
 	 * Don't bother with indexes for an inheritance parent, either.
diff --git a/src/backend/optimizer/util/relnode.c b/src/backend/optimizer/util/relnode.c
@@ -107,6 +107,7 @@ build_simple_rel(PlannerInfo *root, int relid, RelOptKind reloptkind)
 	rel->consider_startup = (root->tuple_fraction > 0);
 	rel->consider_param_startup = false;		/* might get changed later */
 	rel->consider_parallel = false;		/* might get changed later */
+	rel->rel_parallel_degree = -1; /* set up in GetRelationInfo */
 	rel->reltarget = create_empty_pathtarget();
 	rel->pathlist = NIL;
 	rel->ppilist = NIL;
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
@@ -1783,6 +1783,7 @@ psql_completion(const char *text, int start, int end)
 			"autovacuum_vacuum_scale_factor",
 			"autovacuum_vacuum_threshold",
 			"fillfactor",
+			"parallel_degree",
 			"log_autovacuum_min_duration",
 			"toast.autovacuum_enabled",
 			"toast.autovacuum_freeze_max_age",
diff --git a/src/include/nodes/relation.h b/src/include/nodes/relation.h
@@ -522,6 +522,7 @@ typedef struct RelOptInfo
 	double		allvisfrac;
 	PlannerInfo *subroot;		/* if subquery */
 	List	   *subplan_params; /* if subquery */
+	int			rel_parallel_degree;	/* wanted number of parallel workers */
 
 	/* Information about foreign tables and foreign joins */
 	Oid			serverid;		/* identifies server for the table or join */
diff --git a/src/include/utils/rel.h b/src/include/utils/rel.h
@@ -206,6 +206,7 @@ typedef struct StdRdOptions
 	AutoVacOpts autovacuum;		/* autovacuum-related options */
 	bool		user_catalog_table;		/* use as an additional catalog
 										 * relation */
+	int			parallel_degree;	/* max number of parallel workers */
 } StdRdOptions;
 
 #define HEAP_MIN_FILLFACTOR			10
@@ -242,6 +243,14 @@ typedef struct StdRdOptions
 	((relation)->rd_options ?				\
 	 ((StdRdOptions *) (relation)->rd_options)->user_catalog_table : false)
 
+/*
+ * RelationGetParallelDegree
+ *		Returns the relation's parallel_degree.  Note multiple eval of argument!
+ */
+#define RelationGetParallelDegree(relation, defaultpd) \
+	((relation)->rd_options ? \
+	 ((StdRdOptions *) (relation)->rd_options)->parallel_degree : (defaultpd))
+
 
 /*
  * ViewOptions
