Report progress of ANALYZE commands

This uses the progress reporting infrastructure added by c16dc1aca5,
adding support for ANALYZE.

Co-authored-by: Álvaro Herrera <alvherre@alvh.no-ip.org>
Co-authored-by: Tatsuro Yamada <tatsuro.yamada.tf@nttcom.co.jp>
Reviewed-by: Julien Rouhaud, Robert Haas, Anthony Nowocien, Kyotaro Horiguchi,
	Vignesh C, Amit Langote

src/backend/catalog/system_views.sql

@@ -957,6 +957,27 @@ CREATE VIEW pg_stat_bgwriter AS
         pg_stat_get_buf_alloc() AS buffers_alloc,
         pg_stat_get_bgwriter_stat_reset_time() AS stats_reset;
 
+CREATE VIEW pg_stat_progress_analyze AS
+    SELECT
+        S.pid AS pid, S.datid AS datid, D.datname AS datname,
+        CAST(S.relid AS oid) AS relid,
+        CASE S.param1 WHEN 0 THEN 'initializing'
+                      WHEN 1 THEN 'acquiring sample rows'
+                      WHEN 2 THEN 'acquiring inherited sample rows'
+                      WHEN 3 THEN 'computing statistics'
+                      WHEN 4 THEN 'computing extended statistics'
+                      WHEN 5 THEN 'finalizing analyze'
+                      END AS phase,
+        S.param2 AS sample_blks_total,
+        S.param3 AS sample_blks_scanned,
+        S.param4 AS ext_stats_total,
+        S.param5 AS ext_stats_computed,
+        S.param6 AS child_tables_total,
+        S.param7 AS child_tables_done,
+        CAST(S.param8 AS oid) AS current_child_table_relid
+    FROM pg_stat_get_progress_info('ANALYZE') AS S
+        LEFT JOIN pg_database D ON S.datid = D.oid;
+
 CREATE VIEW pg_stat_progress_vacuum AS
     SELECT
         S.pid AS pid, S.datid AS datid, D.datname AS datname,

src/backend/commands/analyze.c

@@ -35,6 +35,7 @@
 #include "catalog/pg_namespace.h"
 #include "catalog/pg_statistic_ext.h"
 #include "commands/dbcommands.h"
+#include "commands/progress.h"
 #include "commands/tablecmds.h"
 #include "commands/vacuum.h"
 #include "executor/executor.h"
@@ -251,6 +252,8 @@ analyze_rel(Oid relid, RangeVar *relation,
 	LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
 	MyPgXact->vacuumFlags |= PROC_IN_ANALYZE;
 	LWLockRelease(ProcArrayLock);
+	pgstat_progress_start_command(PROGRESS_COMMAND_ANALYZE,
+								  RelationGetRelid(onerel));
 
 	/*
 	 * Do the normal non-recursive ANALYZE.  We can skip this for partitioned
@@ -275,6 +278,8 @@ analyze_rel(Oid relid, RangeVar *relation,
 	 */
 	relation_close(onerel, NoLock);
 
+	pgstat_progress_end_command();
+
 	/*
 	 * Reset my PGXACT flag.  Note: we need this here, and not in vacuum_rel,
 	 * because the vacuum flag is cleared by the end-of-xact code.
@@ -506,6 +511,9 @@ do_analyze_rel(Relation onerel, VacuumParams *params,
 	 * Acquire the sample rows
 	 */
 	rows = (HeapTuple *) palloc(targrows * sizeof(HeapTuple));
+	pgstat_progress_update_param(PROGRESS_ANALYZE_PHASE,
+								 inh ? PROGRESS_ANALYZE_PHASE_ACQUIRE_SAMPLE_ROWS_INH :
+								 PROGRESS_ANALYZE_PHASE_ACQUIRE_SAMPLE_ROWS);
 	if (inh)
 		numrows = acquire_inherited_sample_rows(onerel, elevel,
 												rows, targrows,
@@ -526,6 +534,9 @@ do_analyze_rel(Relation onerel, VacuumParams *params,
 		MemoryContext col_context,
 					old_context;
 
+		pgstat_progress_update_param(PROGRESS_ANALYZE_PHASE,
+									 PROGRESS_ANALYZE_PHASE_COMPUTE_STATS);
+
 		col_context = AllocSetContextCreate(anl_context,
 											"Analyze Column",
 											ALLOCSET_DEFAULT_SIZES);
@@ -596,6 +607,9 @@ do_analyze_rel(Relation onerel, VacuumParams *params,
 									   attr_cnt, vacattrstats);
 	}
 
+	pgstat_progress_update_param(PROGRESS_ANALYZE_PHASE,
+								 PROGRESS_ANALYZE_PHASE_FINALIZE_ANALYZE);
+
 	/*
 	 * Update pages/tuples stats in pg_class ... but not if we're doing
 	 * inherited stats.
@@ -1034,6 +1048,8 @@ acquire_sample_rows(Relation onerel, int elevel,
 	ReservoirStateData rstate;
 	TupleTableSlot *slot;
 	TableScanDesc scan;
+	BlockNumber nblocks;
+	BlockNumber blksdone = 0;
 
 	Assert(targrows > 0);
 
@@ -1043,7 +1059,12 @@ acquire_sample_rows(Relation onerel, int elevel,
 	OldestXmin = GetOldestXmin(onerel, PROCARRAY_FLAGS_VACUUM);
 
 	/* Prepare for sampling block numbers */
-	BlockSampler_Init(&bs, totalblocks, targrows, random());
+	nblocks = BlockSampler_Init(&bs, totalblocks, targrows, random());
+
+	/* Report sampling block numbers */
+	pgstat_progress_update_param(PROGRESS_ANALYZE_BLOCKS_TOTAL,
+								 nblocks);
+
 	/* Prepare for sampling rows */
 	reservoir_init_selection_state(&rstate, targrows);
 
@@ -1104,6 +1125,9 @@ acquire_sample_rows(Relation onerel, int elevel,
 
 			samplerows += 1;
 		}
+
+		pgstat_progress_update_param(PROGRESS_ANALYZE_BLOCKS_DONE,
+									 ++blksdone);
 	}
 
 	ExecDropSingleTupleTableSlot(slot);
@@ -1332,6 +1356,8 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 	 * rels have radically different free-space percentages, but it's not
 	 * clear that it's worth working harder.)
 	 */
+	pgstat_progress_update_param(PROGRESS_ANALYZE_CHILD_TABLES_TOTAL,
+								 nrels);
 	numrows = 0;
 	*totalrows = 0;
 	*totaldeadrows = 0;
@@ -1341,6 +1367,9 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		AcquireSampleRowsFunc acquirefunc = acquirefuncs[i];
 		double		childblocks = relblocks[i];
 
+		pgstat_progress_update_param(PROGRESS_ANALYZE_CURRENT_CHILD_TABLE_RELID,
+									 RelationGetRelid(childrel));
+
 		if (childblocks > 0)
 		{
 			int			childtargrows;
@@ -1396,6 +1425,8 @@ acquire_inherited_sample_rows(Relation onerel, int elevel,
 		 * pointers to their TOAST tables in the sampled rows.
 		 */
 		table_close(childrel, NoLock);
+		pgstat_progress_update_param(PROGRESS_ANALYZE_CHILD_TABLES_DONE,
+									 i + 1);
 	}
 
 	return numrows;

src/backend/statistics/extended_stats.c

@@ -24,10 +24,12 @@
 #include "catalog/pg_collation.h"
 #include "catalog/pg_statistic_ext.h"
 #include "catalog/pg_statistic_ext_data.h"
+#include "commands/progress.h"
 #include "miscadmin.h"
 #include "nodes/nodeFuncs.h"
 #include "optimizer/clauses.h"
 #include "optimizer/optimizer.h"
+#include "pgstat.h"
 #include "postmaster/autovacuum.h"
 #include "statistics/extended_stats_internal.h"
 #include "statistics/statistics.h"
@@ -92,6 +94,7 @@ BuildRelationExtStatistics(Relation onerel, double totalrows,
 	List	   *stats;
 	MemoryContext cxt;
 	MemoryContext oldcxt;
+	int64		ext_cnt;
 
 	cxt = AllocSetContextCreate(CurrentMemoryContext,
 								"BuildRelationExtStatistics",
@@ -101,6 +104,22 @@ BuildRelationExtStatistics(Relation onerel, double totalrows,
 	pg_stext = table_open(StatisticExtRelationId, RowExclusiveLock);
 	stats = fetch_statentries_for_relation(pg_stext, RelationGetRelid(onerel));
 
+	/* report this phase */
+	if (stats != NIL)
+	{
+		const int	index[] = {
+			PROGRESS_ANALYZE_PHASE,
+			PROGRESS_ANALYZE_EXT_STATS_TOTAL
+		};
+		const int64 val[] = {
+			PROGRESS_ANALYZE_PHASE_COMPUTE_EXT_STATS,
+			list_length(stats)
+		};
+
+		pgstat_progress_update_multi_param(2, index, val);
+	}
+
+	ext_cnt = 0;
 	foreach(lc, stats)
 	{
 		StatExtEntry *stat = (StatExtEntry *) lfirst(lc);
@@ -165,6 +184,10 @@ BuildRelationExtStatistics(Relation onerel, double totalrows,
 
 		/* store the statistics in the catalog */
 		statext_store(stat->statOid, ndistinct, dependencies, mcv, stats);
+
+		/* for reporting progress */
+		pgstat_progress_update_param(PROGRESS_ANALYZE_EXT_STATS_COMPUTED,
+									 ++ext_cnt);
 	}
 
 	table_close(pg_stext, RowExclusiveLock);

src/backend/utils/adt/pgstatfuncs.c

@@ -468,6 +468,8 @@ pg_stat_get_progress_info(PG_FUNCTION_ARGS)
 	/* Translate command name into command type code. */
 	if (pg_strcasecmp(cmd, "VACUUM") == 0)
 		cmdtype = PROGRESS_COMMAND_VACUUM;
+	else if (pg_strcasecmp(cmd, "ANALYZE") == 0)
+		cmdtype = PROGRESS_COMMAND_ANALYZE;
 	else if (pg_strcasecmp(cmd, "CLUSTER") == 0)
 		cmdtype = PROGRESS_COMMAND_CLUSTER;
 	else if (pg_strcasecmp(cmd, "CREATE INDEX") == 0)

src/backend/utils/misc/sampling.c

@@ -32,8 +32,10 @@
  * Since we know the total number of blocks in advance, we can use the
  * straightforward Algorithm S from Knuth 3.4.2, rather than Vitter's
  * algorithm.
+ *
+ * Returns the number of blocks that BlockSampler_Next will return.
  */
-void
+BlockNumber
 BlockSampler_Init(BlockSampler bs, BlockNumber nblocks, int samplesize,
 				  long randseed)
 {
@@ -48,6 +50,8 @@ BlockSampler_Init(BlockSampler bs, BlockNumber nblocks, int samplesize,
 	bs->m = 0;					/* blocks selected so far */
 
 	sampler_random_init_state(randseed, bs->randstate);
+
+	return Min(bs->n, bs->N);
 }
 
 bool

src/include/catalog/catversion.h

@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	202001091
+#define CATALOG_VERSION_NO	202001151
 
 #endif

src/include/commands/progress.h

@@ -34,6 +34,23 @@
 #define PROGRESS_VACUUM_PHASE_TRUNCATE			5
 #define PROGRESS_VACUUM_PHASE_FINAL_CLEANUP		6
 
+/* Progress parameters for analyze */
+#define PROGRESS_ANALYZE_PHASE						0
+#define PROGRESS_ANALYZE_BLOCKS_TOTAL				1
+#define PROGRESS_ANALYZE_BLOCKS_DONE				2
+#define PROGRESS_ANALYZE_EXT_STATS_TOTAL			3
+#define PROGRESS_ANALYZE_EXT_STATS_COMPUTED			4
+#define PROGRESS_ANALYZE_CHILD_TABLES_TOTAL			5
+#define PROGRESS_ANALYZE_CHILD_TABLES_DONE			6
+#define PROGRESS_ANALYZE_CURRENT_CHILD_TABLE_RELID	7
+
+/* Phases of analyze (as advertised via PROGRESS_ANALYZE_PHASE) */
+#define PROGRESS_ANALYZE_PHASE_ACQUIRE_SAMPLE_ROWS		1
+#define PROGRESS_ANALYZE_PHASE_ACQUIRE_SAMPLE_ROWS_INH	2
+#define PROGRESS_ANALYZE_PHASE_COMPUTE_STATS			3
+#define PROGRESS_ANALYZE_PHASE_COMPUTE_EXT_STATS		4
+#define PROGRESS_ANALYZE_PHASE_FINALIZE_ANALYZE			5
+
 /* Progress parameters for cluster */
 #define PROGRESS_CLUSTER_COMMAND				0
 #define PROGRESS_CLUSTER_PHASE					1

src/include/pgstat.h

@@ -956,6 +956,7 @@ typedef enum ProgressCommandType
 {
 	PROGRESS_COMMAND_INVALID,
 	PROGRESS_COMMAND_VACUUM,
+	PROGRESS_COMMAND_ANALYZE,
 	PROGRESS_COMMAND_CLUSTER,
 	PROGRESS_COMMAND_CREATE_INDEX
 } ProgressCommandType;

src/include/utils/sampling.h

@@ -37,8 +37,8 @@ typedef struct
 
 typedef BlockSamplerData *BlockSampler;
 
-extern void BlockSampler_Init(BlockSampler bs, BlockNumber nblocks,
-							  int samplesize, long randseed);
+extern BlockNumber BlockSampler_Init(BlockSampler bs, BlockNumber nblocks,
+									 int samplesize, long randseed);
 extern bool BlockSampler_HasMore(BlockSampler bs);
 extern BlockNumber BlockSampler_Next(BlockSampler bs);
 

src/test/regress/expected/rules.out

@@ -1852,6 +1852,28 @@ pg_stat_gssapi| SELECT s.pid,
     s.gss_enc AS encrypted
    FROM pg_stat_get_activity(NULL::integer) s(datid, pid, usesysid, application_name, state, query, wait_event_type, wait_event, xact_start, query_start, backend_start, state_change, client_addr, client_hostname, client_port, backend_xid, backend_xmin, backend_type, ssl, sslversion, sslcipher, sslbits, sslcompression, ssl_client_dn, ssl_client_serial, ssl_issuer_dn, gss_auth, gss_princ, gss_enc)
   WHERE (s.client_port IS NOT NULL);
+pg_stat_progress_analyze| SELECT s.pid,
+    s.datid,
+    d.datname,
+    s.relid,
+        CASE s.param1
+            WHEN 0 THEN 'initializing'::text
+            WHEN 1 THEN 'acquiring sample rows'::text
+            WHEN 2 THEN 'acquiring inherited sample rows'::text
+            WHEN 3 THEN 'computing statistics'::text
+            WHEN 4 THEN 'computing extended statistics'::text
+            WHEN 5 THEN 'finalizing analyze'::text
+            ELSE NULL::text
+        END AS phase,
+    s.param2 AS sample_blks_total,
+    s.param3 AS sample_blks_scanned,
+    s.param4 AS ext_stats_total,
+    s.param5 AS ext_stats_computed,
+    s.param6 AS child_tables_total,
+    s.param7 AS child_tables_done,
+    (s.param8)::oid AS current_child_table_relid
+   FROM (pg_stat_get_progress_info('ANALYZE'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10, param11, param12, param13, param14, param15, param16, param17, param18, param19, param20)
+     LEFT JOIN pg_database d ON ((s.datid = d.oid)));
 pg_stat_progress_cluster| SELECT s.pid,
     s.datid,
     d.datname,