From 75be66464cb1bffa1e5757907b9a04ad5afc7859 Mon Sep 17 00:00:00 2001
From: Tom Lane <tgl@sss.pgh.pa.us>
Date: Thu, 16 Jun 2016 13:47:20 -0400
Subject: [PATCH] Invent min_parallel_relation_size GUC to replace a hard-wired
constant.
The main point of doing this is to allow the cutoff to be set very small,
even zero, to allow parallel-query behavior to be tested on relatively
small tables such as we typically use in the regression tests. But it
might be of use to users too. The number-of-workers scaling behavior in
create_plain_partial_paths() is pretty ad-hoc and subject to change, so
we won't expose anything about that, but the notion of not considering
parallel query at all for tables below size X seems reasonably stable.
Amit Kapila, per a suggestion from me
Discussion: <17170.1465830165@sss.pgh.pa.us>
---
doc/src/sgml/config.sgml | 14 ++++++++++++++
src/backend/optimizer/path/allpaths.c | 15 ++++++++++-----
src/backend/utils/misc/guc.c | 11 +++++++++++
src/backend/utils/misc/postgresql.conf.sample | 1 +
src/include/optimizer/paths.h | 1 +
5 files changed, 37 insertions(+), 5 deletions(-)
diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index e0e5a1edc60..a82bf065a06 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -3699,6 +3699,20 @@ include_dir 'conf.d'
</listitem>
</varlistentry>
+ <varlistentry id="guc-min-parallel-relation-size" xreflabel="min_parallel_relation_size">
+ <term><varname>min_parallel_relation_size</varname> (<type>integer</type>)
+ <indexterm>
+ <primary><varname>min_parallel_relation_size</> configuration parameter</primary>
+ </indexterm>
+ </term>
+ <listitem>
+ <para>
+ Sets the minimum size of relations to be considered for parallel scan.
+ The default is 8 megabytes (<literal>8MB</>).
+ </para>
+ </listitem>
+ </varlistentry>
+
<varlistentry id="guc-effective-cache-size" xreflabel="effective_cache_size">
<term><varname>effective_cache_size</varname> (<type>integer</type>)
<indexterm>
diff --git a/src/backend/optimizer/path/allpaths.c b/src/backend/optimizer/path/allpaths.c
index cc8ba61bb0c..2e4b670e069 100644
--- a/src/backend/optimizer/path/allpaths.c
+++ b/src/backend/optimizer/path/allpaths.c
@@ -15,6 +15,7 @@
#include "postgres.h"
+#include <limits.h>
#include <math.h>
#include "access/sysattr.h"
@@ -56,6 +57,7 @@ typedef struct pushdown_safety_info
/* These parameters are set by GUC */
bool enable_geqo = false; /* just in case GUC doesn't set it */
int geqo_threshold;
+int min_parallel_relation_size;
/* Hook for plugins to get control in set_rel_pathlist() */
set_rel_pathlist_hook_type set_rel_pathlist_hook = NULL;
@@ -690,7 +692,7 @@ create_plain_partial_paths(PlannerInfo *root, RelOptInfo *rel)
parallel_workers = rel->rel_parallel_workers;
else
{
- int parallel_threshold = 1000;
+ int parallel_threshold;
/*
* If this relation is too small to be worth a parallel scan, just
@@ -699,21 +701,24 @@ create_plain_partial_paths(PlannerInfo *root, RelOptInfo *rel)
* 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 &&
+ if (rel->pages < (BlockNumber) min_parallel_relation_size &&
rel->reloptkind == RELOPT_BASEREL)
return;
/*
* Select the number of workers based on the log of the size of the
* relation. This probably needs to be a good deal more
- * sophisticated, but we need something here for now.
+ * sophisticated, but we need something here for now. Note that the
+ * upper limit of the min_parallel_relation_size GUC is chosen to
+ * prevent overflow here.
*/
parallel_workers = 1;
- while (rel->pages > parallel_threshold * 3)
+ parallel_threshold = Max(min_parallel_relation_size, 1);
+ while (rel->pages >= (BlockNumber) (parallel_threshold * 3))
{
parallel_workers++;
parallel_threshold *= 3;
- if (parallel_threshold >= PG_INT32_MAX / 3)
+ if (parallel_threshold > INT_MAX / 3)
break; /* avoid overflow */
}
}
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index 9b02111a834..60148b871b3 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -2747,6 +2747,17 @@ static struct config_int ConfigureNamesInt[] =
NULL, NULL, NULL
},
+ {
+ {"min_parallel_relation_size", PGC_USERSET, QUERY_TUNING_COST,
+ gettext_noop("Sets the minimum size of relations to be considered for parallel scan."),
+ NULL,
+ GUC_UNIT_BLOCKS,
+ },
+ &min_parallel_relation_size,
+ 1024, 0, INT_MAX / 3,
+ NULL, NULL, NULL
+ },
+
{
/* Can't be set in postgresql.conf */
{"server_version_num", PGC_INTERNAL, PRESET_OPTIONS,
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index 8260e371bc9..3fa05403bbc 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -304,6 +304,7 @@
#cpu_operator_cost = 0.0025 # same scale as above
#parallel_tuple_cost = 0.1 # same scale as above
#parallel_setup_cost = 1000.0 # same scale as above
+#min_parallel_relation_size = 8MB
#effective_cache_size = 4GB
# - Genetic Query Optimizer -
diff --git a/src/include/optimizer/paths.h b/src/include/optimizer/paths.h
index f3b25e2419c..cc6f85d6dbf 100644
--- a/src/include/optimizer/paths.h
+++ b/src/include/optimizer/paths.h
@@ -22,6 +22,7 @@
*/
extern bool enable_geqo;
extern int geqo_threshold;
+extern int min_parallel_relation_size;
/* Hook for plugins to get control in set_rel_pathlist() */
typedef void (*set_rel_pathlist_hook_type) (PlannerInfo *root,
--
GitLab