New autovacuum_work_mem parameter

If autovacuum_work_mem is set, autovacuum workers now use
this parameter in preference to maintenance_work_mem.

Peter Geoghegan

6 files changed, 69 insertions, 10 deletions

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index f33a16b7aad..8896988e5aa 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -1198,8 +1198,26 @@ include 'filename'
        </para>
        <para>
         Note that when autovacuum runs, up to
-        <xref linkend="guc-autovacuum-max-workers"> times this memory may be
-        allocated, so be careful not to set the default value too high.
+        <xref linkend="guc-autovacuum-max-workers"> times this memory
+        may be allocated, so be careful not to set the default value
+        too high.  It may be useful to control for this by separately
+        setting <xref linkend="guc-autovacuum-work-mem">.
+       </para>
+      </listitem>
+     </varlistentry>
+
+     <varlistentry id="guc-autovacuum-work-mem" xreflabel="autovacuum_work_mem">
+      <term><varname>autovacuum_work_mem</varname> (<type>integer</type>)</term>
+      <indexterm>
+       <primary><varname>autovacuum_work_mem</> configuration parameter</primary>
+      </indexterm>
+      <listitem>
+       <para>
+        Specifies the maximum amount of memory to be used by each
+        autovacuum worker process.  It defaults to -1, indicating that
+        the value of <xref linkend="guc-maintenance-work-mem"> should
+        be used instead.  The setting has no effect on the behavior of
+        <command>VACUUM</command> when run in other contexts.
        </para>
       </listitem>
      </varlistentry>
diff --git a/src/backend/commands/vacuumlazy.c b/src/backend/commands/vacuumlazy.c
index d346772600c..7b9837f4f42 100644
--- a/src/backend/commands/vacuumlazy.c
+++ b/src/backend/commands/vacuumlazy.c
@@ -10,13 +10,13 @@
  * relations with finite memory space usage.  To do that, we set upper bounds
  * on the number of tuples and pages we will keep track of at once.
  *
- * We are willing to use at most maintenance_work_mem memory space to keep
- * track of dead tuples.  We initially allocate an array of TIDs of that size,
- * with an upper limit that depends on table size (this limit ensures we don't
- * allocate a huge area uselessly for vacuuming small tables).	If the array
- * threatens to overflow, we suspend the heap scan phase and perform a pass of
- * index cleanup and page compaction, then resume the heap scan with an empty
- * TID array.
+ * We are willing to use at most maintenance_work_mem (or perhaps
+ * autovacuum_work_mem) memory space to keep track of dead tuples.  We
+ * initially allocate an array of TIDs of that size, with an upper limit that
+ * depends on table size (this limit ensures we don't allocate a huge area
+ * uselessly for vacuuming small tables).  If the array threatens to overflow,
+ * we suspend the heap scan phase and perform a pass of index cleanup and page
+ * compaction, then resume the heap scan with an empty TID array.
  *
  * If we're processing a table with no indexes, we can just vacuum each page
  * as we go; there's no need to save up multiple tuples to minimize the number
@@ -1599,10 +1599,13 @@ static void
 lazy_space_alloc(LVRelStats *vacrelstats, BlockNumber relblocks)
 {
 	long		maxtuples;
+	int			vac_work_mem =  IsAutoVacuumWorkerProcess() &&
+									autovacuum_work_mem != -1 ?
+								autovacuum_work_mem : maintenance_work_mem;
 
 	if (vacrelstats->hasindex)
 	{
-		maxtuples = (maintenance_work_mem * 1024L) / sizeof(ItemPointerData);
+		maxtuples = (vac_work_mem * 1024L) / sizeof(ItemPointerData);
 		maxtuples = Min(maxtuples, INT_MAX);
 		maxtuples = Min(maxtuples, MaxAllocSize / sizeof(ItemPointerData));
 
diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 88ecd3834b3..be370b19f98 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -110,6 +110,7 @@
  */
 bool		autovacuum_start_daemon = false;
 int			autovacuum_max_workers;
+int			autovacuum_work_mem = -1;
 int			autovacuum_naptime;
 int			autovacuum_vac_thresh;
 double		autovacuum_vac_scale;
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index f3bf6e0aa2f..e69e132f056 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -194,6 +194,7 @@ static const char *show_tcp_keepalives_count(void);
 static bool check_maxconnections(int *newval, void **extra, GucSource source);
 static bool check_max_worker_processes(int *newval, void **extra, GucSource source);
 static bool check_autovacuum_max_workers(int *newval, void **extra, GucSource source);
+static bool check_autovacuum_work_mem(int *newval, void **extra, GucSource source);
 static bool check_effective_io_concurrency(int *newval, void **extra, GucSource source);
 static void assign_effective_io_concurrency(int newval, void *extra);
 static void assign_pgstat_temp_directory(const char *newval, void *extra);
@@ -2358,6 +2359,17 @@ static struct config_int ConfigureNamesInt[] =
 	},
 
 	{
+		{"autovacuum_work_mem", PGC_SIGHUP, RESOURCES_MEM,
+			gettext_noop("Sets the maximum memory to be used by each autovacuum worker process."),
+			NULL,
+			GUC_UNIT_KB
+		},
+		&autovacuum_work_mem,
+		-1, -1, MAX_KILOBYTES,
+		check_autovacuum_work_mem, NULL, NULL
+	},
+
+	{
 		{"tcp_keepalives_idle", PGC_USERSET, CLIENT_CONN_OTHER,
 			gettext_noop("Time between issuing TCP keepalives."),
 			gettext_noop("A value of 0 uses the system default."),
@@ -8778,6 +8790,29 @@ check_autovacuum_max_workers(int *newval, void **extra, GucSource source)
 }
 
 static bool
+check_autovacuum_work_mem(int *newval, void **extra, GucSource source)
+{
+	/*
+	 * -1 indicates fallback.
+	 *
+	 * If we haven't yet changed the boot_val default of -1, just let it be.
+	 * Autovacuum will look to maintenance_work_mem instead.
+	 */
+	if (*newval == -1)
+		return true;
+
+	/*
+	 * We clamp manually-set values to at least 1MB.  Since
+	 * maintenance_work_mem is always set to at least this value, do the same
+	 * here.
+	 */
+	if (*newval < 1024)
+		*newval = 1024;
+
+	return true;
+}
+
+static bool
 check_max_worker_processes(int *newval, void **extra, GucSource source)
 {
 	if (MaxConnections + autovacuum_max_workers + 1 + *newval > MAX_BACKENDS)
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index 6096fe44457..f8bdce34d33 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -124,6 +124,7 @@
 # actively intend to use prepared transactions.
 #work_mem = 1MB				# min 64kB
 #maintenance_work_mem = 16MB		# min 1MB
+#autovacuum_work_mem = -1		# min 1MB, or -1 to use maintenance_work_mem
 #max_stack_depth = 2MB			# min 100kB
 #dynamic_shared_memory_type = posix # the default is the first option
 					# supported by the operating system:
diff --git a/src/include/postmaster/autovacuum.h b/src/include/postmaster/autovacuum.h
index e96f07aaff9..92560fe2177 100644
--- a/src/include/postmaster/autovacuum.h
+++ b/src/include/postmaster/autovacuum.h
@@ -18,6 +18,7 @@
 /* GUC variables */
 extern bool autovacuum_start_daemon;
 extern int	autovacuum_max_workers;
+extern int	autovacuum_work_mem;
 extern int	autovacuum_naptime;
 extern int	autovacuum_vac_thresh;
 extern double autovacuum_vac_scale;