v11-Report-progress-for-ANALYZE.patch

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index a3c5f86b7e..a5da126b8f 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -360,6 +360,14 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
       </entry>
      </row>
 
+     <row>
+      <entry><structname>pg_stat_progress_analyze</structname><indexterm><primary>pg_stat_progress_analyze</primary></indexterm></entry>
+      <entry>One row for each backend (including autovacuum worker processes) running
+       <command>ANALYZE</command>, showing current progress.
+       See <xref linkend='analyze-progress-reporting'/>.
+      </entry>
+     </row>
+
      <row>
       <entry><structname>pg_stat_progress_cluster</structname><indexterm><primary>pg_stat_progress_cluster</primary></indexterm></entry>
       <entry>One row for each backend running
@@ -3502,7 +3510,7 @@ SELECT pg_stat_get_backend_pid(s.backendid) AS pid,
    <productname>PostgreSQL</productname> has the ability to report the progress of
    certain commands during command execution.  Currently, the only commands
    which support progress reporting are <command>CREATE INDEX</command>,
-   <command>VACUUM</command> and
+   <command>VACUUM</command>, <command>ANALYZE</command> and
    <command>CLUSTER</command>. This may be expanded in the future.
   </para>
 
@@ -3948,6 +3956,179 @@ SELECT pg_stat_get_backend_pid(s.backendid) AS pid,
 
  </sect2>
 
+ <sect2 id="analyze-progress-reporting">
+  <title>ANALYZE Progress Reporting</title>
+
+  <para>
+   Whenever <command>ANALYZE</command> is running, the
+   <structname>pg_stat_progress_analyze</structname> view will contain a
+   row for each backend that is currently running that command.  The tables
+   below describe the information that will be reported and provide
+   information about how to interpret it.
+  </para>
+
+  <table id="pg-stat-progress-analyze-view" xreflabel="pg_stat_progress_analyze">
+   <title><structname>pg_stat_progress_analyze</structname> View</title>
+   <tgroup cols="3">
+    <thead>
+    <row>
+      <entry>Column</entry>
+      <entry>Type</entry>
+      <entry>Description</entry>
+     </row>
+    </thead>
+
+   <tbody>
+    <row>
+     <entry><structfield>pid</structfield></entry>
+     <entry><type>integer</type></entry>
+     <entry>Process ID of backend.</entry>
+    </row>
+    <row>
+     <entry><structfield>datid</structfield></entry>
+     <entry><type>oid</type></entry>
+     <entry>OID of the database to which this backend is connected.</entry>
+    </row>
+    <row>
+     <entry><structfield>datname</structfield></entry>
+     <entry><type>name</type></entry>
+     <entry>Name of the database to which this backend is connected.</entry>
+    </row>
+    <row>
+     <entry><structfield>relid</structfield></entry>
+     <entry><type>oid</type></entry>
+     <entry>OID of the table being analyzed.</entry>
+    </row>
+    <row>
+     <entry><structfield>phase</structfield></entry>
+     <entry><type>text</type></entry>
+     <entry>Current processing phase. See <xref linkend="analyze-phases" /></entry>
+    </row>
+    <row>
+     <entry><structfield>sample_blks_total</structfield></entry>
+     <entry><type>bigint</type></entry>
+     <entry>
+       Total number of heap blocks that will be sampled.
+     </entry>
+    </row>
+    <row>
+     <entry><structfield>sample_blks_scanned</structfield></entry>
+     <entry><type>bigint</type></entry>
+     <entry>
+       Number of heap blocks scanned.
+     </entry>
+    </row>
+    <row>
+     <entry><structfield>ext_stats_total</structfield></entry>
+     <entry><type>bigint</type></entry>
+     <entry>
+       Number of extended statistics.
+     </entry>
+    </row>
+    <row>
+     <entry><structfield>ext_stats_computed</structfield></entry>
+     <entry><type>bigint</type></entry>
+     <entry>
+       Number of computed extended statistics computed.  This counter only advances when
+       the phase is <literal>computing extended statistics</literal>.
+     </entry>
+    </row>
+    <row>
+     <entry><structfield>child_tables_total</structfield></entry>
+     <entry><type>bigint</type></entry>
+     <entry>
+       Number of child tables.
+     </entry>
+    </row>
+    <row>
+     <entry><structfield>child_tables_done</structfield></entry>
+     <entry><type>bigint</type></entry>
+     <entry>
+       Number of child tables scanned.  This counter only advances when the phase
+       is <literal>acquiring inherited sample rows</literal>.
+     </entry>
+    </row>
+    <row>
+     <entry><structfield>current_child_table_relid</structfield></entry>
+     <entry><type>oid</type></entry>
+     <entry>OID of the child table currently being scanned. This field is only valid when
+       the phase is <literal>computing extended statistics</literal>.
+     </entry>
+    </row>
+   </tbody>
+   </tgroup>
+  </table>
+
+  <table id="analyze-phases">
+   <title>ANALYZE phases</title>
+   <tgroup cols="2">
+    <thead>
+    <row>
+      <entry>Phase</entry>
+      <entry>Description</entry>
+     </row>
+    </thead>
+   <tbody>
+    <row>
+     <entry><literal>initializing</literal></entry>
+     <entry>
+       The command is preparing to begin scanning the heap.  This phase is
+       expected to be very brief.
+     </entry>
+    </row>
+    <row>
+     <entry><literal>acquiring sample rows</literal></entry>
+     <entry>
+       The command is currently scanning the table given by
+       <structfield>current_relid</structfield> to obtain sample rows.
+     </entry>
+    </row>
+    <row>
+     <entry><literal>acquiring inherited sample rows</literal></entry>
+     <entry>
+       The command is currently scanning child tables to obtain sample rows. Columns
+       <structfield>child_tables_total</structfield>,
+       <structfield>child_tables_done</structfield>, and
+       <structfield>current_child_table_relid</structfield> contain the progress
+       information for this phase.
+     </entry>
+    </row>
+    <row>
+     <entry><literal>computing statistics</literal></entry>
+     <entry>
+       The command is computing statistics from the samples rows obtained during
+       the table scan.
+     </entry>
+    </row>
+    <row>
+     <entry><literal>computing extended statistics</literal></entry>
+     <entry>
+       The command is computing extended statistics from the samples rows obtained
+       durring the table scan.
+     </entry>
+    </row>
+    <row>
+     <entry><literal>finalizing analyze</literal></entry>
+     <entry>
+       The command is updating pg_class. When this phase is completed, 
+       <command>ANALYZE</command> will end.
+     </entry>
+    </row>
+   </tbody>
+   </tgroup>
+  </table>
+
+  <note>
+   <para>
+    Note that when <command>ANALYZE</command> is run on a partitioned table,
+    all of its partitions are also recursively analyzed as also mentioned on
+    <xref linkend="sql-analyze"/>.  In that case, <command>ANALYZE</command>
+    progress is reported first for the parent table, whereby its inheritance
+    statistics are collected, followed by that for each partition.
+   </para>
+  </note>
+ </sect2>
+
  <sect2 id="cluster-progress-reporting">
   <title>CLUSTER Progress Reporting</title>
 
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index f7800f01a6..40195de1a5 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -969,6 +969,27 @@ CREATE VIEW pg_stat_progress_vacuum AS
     FROM pg_stat_get_progress_info('VACUUM') AS S
         LEFT JOIN pg_database D ON S.datid = D.oid;
 
+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_cluster AS
     SELECT
         S.pid AS pid,
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 71372ceb16..187e619170 100644
--- a/src/backend/commands/analyze.c
+++ b/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.
@@ -507,13 +512,23 @@ do_analyze_rel(Relation onerel, VacuumParams *params,
 	 */
 	rows = (HeapTuple *) palloc(targrows * sizeof(HeapTuple));
 	if (inh)
+	{
+		pgstat_progress_update_param(PROGRESS_ANALYZE_PHASE,
+									 PROGRESS_ANALYZE_PHASE_ACQUIRE_INHERITED_SAMPLE_ROWS);
+
 		numrows = acquire_inherited_sample_rows(onerel, elevel,
 												rows, targrows,
 												&totalrows, &totaldeadrows);
+	}
 	else
+	{
+		pgstat_progress_update_param(PROGRESS_ANALYZE_PHASE,
+									 PROGRESS_ANALYZE_PHASE_ACQUIRE_SAMPLE_ROWS);
+
 		numrows = (*acquirefunc) (onerel, elevel,
 								  rows, targrows,
 								  &totalrows, &totaldeadrows);
+	}
 
 	/*
 	 * Compute the statistics.  Temporary results during the calculations for
@@ -524,7 +539,10 @@ do_analyze_rel(Relation onerel, VacuumParams *params,
 	if (numrows > 0)
 	{
 		MemoryContext col_context,
-					old_context;
+					  old_context;
+
+		pgstat_progress_update_param(PROGRESS_ANALYZE_PHASE,
+									 PROGRESS_ANALYZE_PHASE_COMPUTE_STATS);
 
 		col_context = AllocSetContextCreate(anl_context,
 											"Analyze Column",
@@ -592,10 +610,18 @@ do_analyze_rel(Relation onerel, VacuumParams *params,
 		 * not for relations representing inheritance trees.
 		 */
 		if (!inh)
+		{
+			pgstat_progress_update_param(PROGRESS_ANALYZE_PHASE,
+										 PROGRESS_ANALYZE_PHASE_COMPUTE_EXT_STATS);
+
 			BuildRelationExtStatistics(onerel, totalrows, numrows, rows,
 									   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 +1060,8 @@ acquire_sample_rows(Relation onerel, int elevel,
 	ReservoirStateData rstate;
 	TupleTableSlot *slot;
 	TableScanDesc scan;
+	BlockNumber	nblocks;
+	BlockNumber	blksdone = 0;
 
 	Assert(targrows > 0);
 
@@ -1043,7 +1071,12 @@ 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 +1137,9 @@ acquire_sample_rows(Relation onerel, int elevel,
 
 			samplerows += 1;
 		}
+
+		pgstat_progress_update_param(PROGRESS_ANALYZE_BLOCKS_DONE,
+									 ++blksdone);
 	}
 
 	ExecDropSingleTupleTableSlot(slot);
@@ -1332,6 +1368,8 @@ 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 +1379,9 @@ 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 +1437,8 @@ 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;
diff --git a/src/backend/statistics/extended_stats.c b/src/backend/statistics/extended_stats.c
index 9d339433f6..5bbdf6d820 100644
--- a/src/backend/statistics/extended_stats.c
+++ b/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 +104,11 @@ BuildRelationExtStatistics(Relation onerel, double totalrows,
 	pg_stext = table_open(StatisticExtRelationId, RowExclusiveLock);
 	stats = fetch_statentries_for_relation(pg_stext, RelationGetRelid(onerel));
 
+	/* for reporting progress */
+	pgstat_progress_update_param(PROGRESS_ANALYZE_EXT_STATS_TOTAL,
+								 list_length(stats));
+
+	ext_cnt = 0;
 	foreach(lc, stats)
 	{
 		StatExtEntry *stat = (StatExtEntry *) lfirst(lc);
@@ -165,6 +173,10 @@ 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);
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 05240bfd14..db2cc5c316 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -469,6 +469,8 @@ 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)
diff --git a/src/backend/utils/misc/sampling.c b/src/backend/utils/misc/sampling.c
index d2a1537979..f7daece5ee 100644
--- a/src/backend/utils/misc/sampling.c
+++ b/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
diff --git a/src/include/commands/progress.h b/src/include/commands/progress.h
index acd1313cb3..c29c1e00fc 100644
--- a/src/include/commands/progress.h
+++ b/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_INHERITED_SAMPLE_ROWS	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
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index fe076d823d..df418af4e7 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -955,6 +955,7 @@ typedef enum ProgressCommandType
 {
 	PROGRESS_COMMAND_INVALID,
 	PROGRESS_COMMAND_VACUUM,
+	PROGRESS_COMMAND_ANALYZE,
 	PROGRESS_COMMAND_CLUSTER,
 	PROGRESS_COMMAND_CREATE_INDEX
 } ProgressCommandType;
diff --git a/src/include/utils/sampling.h b/src/include/utils/sampling.h
index 541b507fb5..76d31dc126 100644
--- a/src/include/utils/sampling.h
+++ b/src/include/utils/sampling.h
@@ -37,7 +37,7 @@ typedef struct
 
 typedef BlockSamplerData *BlockSampler;
 
-extern void BlockSampler_Init(BlockSampler bs, BlockNumber nblocks,
+extern BlockNumber BlockSampler_Init(BlockSampler bs, BlockNumber nblocks,
 							  int samplesize, long randseed);
 extern bool BlockSampler_HasMore(BlockSampler bs);
 extern BlockNumber BlockSampler_Next(BlockSampler bs);
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index 80a07825b9..eb21983a55 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1847,6 +1847,28 @@ 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,