Make EXPLAIN (BUFFERS) track blocks dirtied, as well as those written.

Also expose the new counters through pg_stat_statements.

Patch by me.  Review by Fujii Masao and Greg Smith.

Author: robertmhaas

contrib/pg_stat_statements/Makefile

@@ -4,7 +4,8 @@ MODULE_big = pg_stat_statements
 OBJS = pg_stat_statements.o
 
 EXTENSION = pg_stat_statements
-DATA = pg_stat_statements--1.0.sql pg_stat_statements--unpackaged--1.0.sql
+DATA = pg_stat_statements--1.1.sql pg_stat_statements--1.0--1.1.sql \
+	pg_stat_statements--unpackaged--1.0.sql
 
 ifdef USE_PGXS
 PG_CONFIG = pg_config

contrib/pg_stat_statements/pg_stat_statements--1.0--1.1.sql

@@ -0,0 +1,40 @@
+/* contrib/pg_stat_statements/pg_stat_statements--1.0--1.1.sql */
+
+-- complain if script is sourced in psql, rather than via ALTER EXTENSION
+\echo Use "ALTER EXTENSION pg_stat_statements UPDATE" to load this file. \quit
+
+/* First we have to remove them from the extension */
+ALTER EXTENSION pg_stat_statements DROP VIEW pg_stat_statements;
+ALTER EXTENSION pg_stat_statements DROP FUNCTION pg_stat_statements();
+
+/* Then we can drop them */
+DROP VIEW pg_stat_statements;
+DROP FUNCTION pg_stat_statements();
+
+/* Now redefine */
+CREATE FUNCTION pg_stat_statements(
+    OUT userid oid,
+    OUT dbid oid,
+    OUT query text,
+    OUT calls int8,
+    OUT total_time float8,
+    OUT rows int8,
+    OUT shared_blks_hit int8,
+    OUT shared_blks_read int8,
+    OUT shared_blks_dirtied int8,
+    OUT shared_blks_written int8,
+    OUT local_blks_hit int8,
+    OUT local_blks_read int8,
+    OUT local_blks_dirtied int8,
+    OUT local_blks_written int8,
+    OUT temp_blks_read int8,
+    OUT temp_blks_written int8
+)
+RETURNS SETOF record
+AS 'MODULE_PATHNAME'
+LANGUAGE C;
+
+CREATE VIEW pg_stat_statements AS
+  SELECT * FROM pg_stat_statements();
+
+GRANT SELECT ON pg_stat_statements TO PUBLIC;

contrib/pg_stat_statements/pg_stat_statements--1.1.sql

@@ -0,0 +1,41 @@
+/* contrib/pg_stat_statements/pg_stat_statements--1.1.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_stat_statements" to load this file. \quit
+
+-- Register functions.
+CREATE FUNCTION pg_stat_statements_reset()
+RETURNS void
+AS 'MODULE_PATHNAME'
+LANGUAGE C;
+
+CREATE FUNCTION pg_stat_statements(
+    OUT userid oid,
+    OUT dbid oid,
+    OUT query text,
+    OUT calls int8,
+    OUT total_time float8,
+    OUT rows int8,
+    OUT shared_blks_hit int8,
+    OUT shared_blks_read int8,
+    OUT shared_blks_dirtied int8,
+    OUT shared_blks_written int8,
+    OUT local_blks_hit int8,
+    OUT local_blks_read int8,
+    OUT local_blks_dirtied int8,
+    OUT local_blks_written int8,
+    OUT temp_blks_read int8,
+    OUT temp_blks_written int8
+)
+RETURNS SETOF record
+AS 'MODULE_PATHNAME'
+LANGUAGE C;
+
+-- Register a view on the function for ease of use.
+CREATE VIEW pg_stat_statements AS
+  SELECT * FROM pg_stat_statements();
+
+GRANT SELECT ON pg_stat_statements TO PUBLIC;
+
+-- Don't want this to be available to non-superusers.
+REVOKE ALL ON FUNCTION pg_stat_statements_reset() FROM PUBLIC;

contrib/pg_stat_statements/pg_stat_statements.c

@@ -77,9 +77,11 @@ typedef struct Counters
 	int64		rows;			/* total # of retrieved or affected rows */
 	int64		shared_blks_hit;	/* # of shared buffer hits */
 	int64		shared_blks_read;		/* # of shared disk blocks read */
+	int64		shared_blks_dirtied;	/* # of shared disk blocks dirtied */
 	int64		shared_blks_written;	/* # of shared disk blocks written */
 	int64		local_blks_hit; /* # of local buffer hits */
 	int64		local_blks_read;	/* # of local disk blocks read */
+	int64		local_blks_dirtied;		/* # of local disk blocks dirtied */
 	int64		local_blks_written;		/* # of local disk blocks written */
 	int64		temp_blks_read; /* # of temp blocks read */
 	int64		temp_blks_written;		/* # of temp blocks written */
@@ -652,12 +654,16 @@ pgss_ProcessUtility(Node *parsetree, const char *queryString,
 			pgBufferUsage.shared_blks_hit - bufusage.shared_blks_hit;
 		bufusage.shared_blks_read =
 			pgBufferUsage.shared_blks_read - bufusage.shared_blks_read;
+		bufusage.shared_blks_dirtied =
+			pgBufferUsage.shared_blks_dirtied - bufusage.shared_blks_dirtied;
 		bufusage.shared_blks_written =
 			pgBufferUsage.shared_blks_written - bufusage.shared_blks_written;
 		bufusage.local_blks_hit =
 			pgBufferUsage.local_blks_hit - bufusage.local_blks_hit;
 		bufusage.local_blks_read =
 			pgBufferUsage.local_blks_read - bufusage.local_blks_read;
+		bufusage.local_blks_dirtied =
+			pgBufferUsage.local_blks_dirtied - bufusage.local_blks_dirtied;
 		bufusage.local_blks_written =
 			pgBufferUsage.local_blks_written - bufusage.local_blks_written;
 		bufusage.temp_blks_read =
@@ -766,9 +772,11 @@ pgss_store(const char *query, double total_time, uint64 rows,
 		e->counters.rows += rows;
 		e->counters.shared_blks_hit += bufusage->shared_blks_hit;
 		e->counters.shared_blks_read += bufusage->shared_blks_read;
+		e->counters.shared_blks_dirtied += bufusage->shared_blks_dirtied;
 		e->counters.shared_blks_written += bufusage->shared_blks_written;
 		e->counters.local_blks_hit += bufusage->local_blks_hit;
 		e->counters.local_blks_read += bufusage->local_blks_read;
+		e->counters.local_blks_dirtied += bufusage->local_blks_dirtied;
 		e->counters.local_blks_written += bufusage->local_blks_written;
 		e->counters.temp_blks_read += bufusage->temp_blks_read;
 		e->counters.temp_blks_written += bufusage->temp_blks_written;
@@ -793,7 +801,8 @@ pg_stat_statements_reset(PG_FUNCTION_ARGS)
 	PG_RETURN_VOID();
 }
 
-#define PG_STAT_STATEMENTS_COLS		14
+#define PG_STAT_STATEMENTS_COLS_V1_0	14
+#define PG_STAT_STATEMENTS_COLS			16
 
 /*
  * Retrieve statement statistics.
@@ -810,6 +819,7 @@ pg_stat_statements(PG_FUNCTION_ARGS)
 	bool		is_superuser = superuser();
 	HASH_SEQ_STATUS hash_seq;
 	pgssEntry  *entry;
+	bool		sql_supports_dirty_counters = true;
 
 	if (!pgss || !pgss_hash)
 		ereport(ERROR,
@@ -830,6 +840,8 @@ pg_stat_statements(PG_FUNCTION_ARGS)
 	/* Build a tuple descriptor for our result type */
 	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
 		elog(ERROR, "return type must be a row type");
+	if (tupdesc->natts == PG_STAT_STATEMENTS_COLS_V1_0)
+		sql_supports_dirty_counters = false;
 
 	per_query_ctx = rsinfo->econtext->ecxt_per_query_memory;
 	oldcontext = MemoryContextSwitchTo(per_query_ctx);
@@ -887,14 +899,19 @@ pg_stat_statements(PG_FUNCTION_ARGS)
 		values[i++] = Int64GetDatumFast(tmp.rows);
 		values[i++] = Int64GetDatumFast(tmp.shared_blks_hit);
 		values[i++] = Int64GetDatumFast(tmp.shared_blks_read);
+		if (sql_supports_dirty_counters)
+			values[i++] = Int64GetDatumFast(tmp.shared_blks_dirtied);
 		values[i++] = Int64GetDatumFast(tmp.shared_blks_written);
 		values[i++] = Int64GetDatumFast(tmp.local_blks_hit);
 		values[i++] = Int64GetDatumFast(tmp.local_blks_read);
+		if (sql_supports_dirty_counters)
+			values[i++] = Int64GetDatumFast(tmp.local_blks_dirtied);
 		values[i++] = Int64GetDatumFast(tmp.local_blks_written);
 		values[i++] = Int64GetDatumFast(tmp.temp_blks_read);
 		values[i++] = Int64GetDatumFast(tmp.temp_blks_written);
 
-		Assert(i == PG_STAT_STATEMENTS_COLS);
+		Assert(i == sql_supports_dirty_counters ? \
+			PG_STAT_STATEMENTS_COLS : PG_STAT_STATEMENTS_COLS_V1_0);
 
 		tuplestore_putvalues(tupstore, tupdesc, values, nulls);
 	}

contrib/pg_stat_statements/pg_stat_statements.control

@@ -1,5 +1,5 @@
 # pg_stat_statements extension
 comment = 'track execution statistics of all SQL statements executed'
-default_version = '1.0'
+default_version = '1.1'
 module_pathname = '$libdir/pg_stat_statements'
 relocatable = true

doc/src/sgml/pgstatstatements.sgml

@@ -99,6 +99,13 @@
       <entry>Total number of shared blocks reads by the statement</entry>
      </row>
 
+     <row>
+      <entry><structfield>shared_blks_dirtied</structfield></entry>
+      <entry><type>bigint</type></entry>
+      <entry></entry>
+      <entry>Total number of shared blocks dirtied by the statement</entry>
+     </row>
+
      <row>
       <entry><structfield>shared_blks_written</structfield></entry>
       <entry><type>bigint</type></entry>
@@ -120,6 +127,13 @@
       <entry>Total number of local blocks reads by the statement</entry>
      </row>
 
+     <row>
+      <entry><structfield>local_blks_dirtied</structfield></entry>
+      <entry><type>bigint</type></entry>
+      <entry></entry>
+      <entry>Total number of local blocks dirtied by the statement</entry>
+     </row>
+
      <row>
       <entry><structfield>local_blks_written</structfield></entry>
       <entry><type>bigint</type></entry>

doc/src/sgml/ref/explain.sgml

@@ -155,14 +155,20 @@ ROLLBACK;
     <listitem>
      <para>
       Include information on buffer usage. Specifically, include the number of
-      shared blocks hits, reads, and writes, the number of local blocks hits,
-      reads, and writes, and the number of temp blocks reads and writes.
-      A <quote>hit</> means that a read was avoided because the block was
+      shared blocks hit, read, dirtied, and written, the number of local blocks
+      hit, read, dirtied, and written, and the number of temp blocks read and
+      written.
+      A <emphasis>hit</> means that a read was avoided because the block was
       found already in cache when needed.
       Shared blocks contain data from regular tables and indexes;
       local blocks contain data from temporary tables and indexes;
       while temp blocks contain short-term working data used in sorts, hashes,
       Materialize plan nodes, and similar cases.
+      The number of blocks <emphasis>dirtied</> indicates the number of
+      previously unmodified blocks that were changed by this query; while the
+      number of blocks <emphasis>written</> indicates the number of
+      previously-dirtied blocks evicted from cache by this backend during
+      query processing.
       The number of blocks shown for an
       upper-level node includes those used by all its child nodes.  In text
       format, only non-zero values are printed.  This parameter may only be

src/backend/commands/explain.c

@@ -1183,12 +1183,14 @@ ExplainNode(PlanState *planstate, List *ancestors,
 		{
 			bool		has_shared = (usage->shared_blks_hit > 0 ||
 									  usage->shared_blks_read > 0 ||
-									  usage->shared_blks_written);
+									  usage->shared_blks_dirtied > 0 ||
+									  usage->shared_blks_written > 0);
 			bool		has_local = (usage->local_blks_hit > 0 ||
 									 usage->local_blks_read > 0 ||
-									 usage->local_blks_written);
+									 usage->local_blks_dirtied > 0 ||
+									 usage->local_blks_written > 0);
 			bool		has_temp = (usage->temp_blks_read > 0 ||
-									usage->temp_blks_written);
+									usage->temp_blks_written > 0);
 
 			/* Show only positive counter values. */
 			if (has_shared || has_local || has_temp)
@@ -1205,6 +1207,9 @@ ExplainNode(PlanState *planstate, List *ancestors,
 					if (usage->shared_blks_read > 0)
 						appendStringInfo(es->str, " read=%ld",
 										 usage->shared_blks_read);
+					if (usage->shared_blks_dirtied > 0)
+						appendStringInfo(es->str, " dirtied=%ld",
+										 usage->shared_blks_dirtied);
 					if (usage->shared_blks_written > 0)
 						appendStringInfo(es->str, " written=%ld",
 										 usage->shared_blks_written);
@@ -1220,6 +1225,9 @@ ExplainNode(PlanState *planstate, List *ancestors,
 					if (usage->local_blks_read > 0)
 						appendStringInfo(es->str, " read=%ld",
 										 usage->local_blks_read);
+					if (usage->local_blks_dirtied > 0)
+						appendStringInfo(es->str, " dirtied=%ld",
+										 usage->local_blks_dirtied);
 					if (usage->local_blks_written > 0)
 						appendStringInfo(es->str, " written=%ld",
 										 usage->local_blks_written);
@@ -1243,9 +1251,11 @@ ExplainNode(PlanState *planstate, List *ancestors,
 		{
 			ExplainPropertyLong("Shared Hit Blocks", usage->shared_blks_hit, es);
 			ExplainPropertyLong("Shared Read Blocks", usage->shared_blks_read, es);
+			ExplainPropertyLong("Shared Dirtied Blocks", usage->shared_blks_dirtied, es);
 			ExplainPropertyLong("Shared Written Blocks", usage->shared_blks_written, es);
 			ExplainPropertyLong("Local Hit Blocks", usage->local_blks_hit, es);
 			ExplainPropertyLong("Local Read Blocks", usage->local_blks_read, es);
+			ExplainPropertyLong("Local Dirtied Blocks", usage->local_blks_dirtied, es);
 			ExplainPropertyLong("Local Written Blocks", usage->local_blks_written, es);
 			ExplainPropertyLong("Temp Read Blocks", usage->temp_blks_read, es);
 			ExplainPropertyLong("Temp Written Blocks", usage->temp_blks_written, es);

src/backend/executor/instrument.c

@@ -137,9 +137,11 @@ BufferUsageAccumDiff(BufferUsage *dst,
 {
 	dst->shared_blks_hit += add->shared_blks_hit - sub->shared_blks_hit;
 	dst->shared_blks_read += add->shared_blks_read - sub->shared_blks_read;
+	dst->shared_blks_dirtied += add->shared_blks_dirtied - sub->shared_blks_dirtied;
 	dst->shared_blks_written += add->shared_blks_written - sub->shared_blks_written;
 	dst->local_blks_hit += add->local_blks_hit - sub->local_blks_hit;
 	dst->local_blks_read += add->local_blks_read - sub->local_blks_read;
+	dst->local_blks_dirtied += add->local_blks_dirtied - sub->local_blks_dirtied;
 	dst->local_blks_written += add->local_blks_written - sub->local_blks_written;
 	dst->temp_blks_read += add->temp_blks_read - sub->temp_blks_read;
 	dst->temp_blks_written += add->temp_blks_written - sub->temp_blks_written;

src/backend/storage/buffer/bufmgr.c

@@ -988,6 +988,7 @@ MarkBufferDirty(Buffer buffer)
 	if (dirtied)
 	{
 		VacuumPageDirty++;
+		pgBufferUsage.shared_blks_dirtied++;
 		if (VacuumCostActive)
 			VacuumCostBalance += VacuumCostPageDirty;
 		if (ProcGlobal->bgwriterLatch)