v20250225-0003-progress.patch

From 8df37528e0ccab135fad3a9182fb448183a413ee Mon Sep 17 00:00:00 2001
From: Tomas Vondra <tomas@vondra.me>
Date: Tue, 25 Feb 2025 15:40:59 +0100
Subject: [PATCH v20250225 3/7] progress

---
 src/backend/access/gin/gininsert.c | 61 ++++++++++++++++++++++++++++--
 src/backend/access/gin/ginutil.c   | 28 +++++++++++++-
 src/include/access/gin.h           | 11 ++++++
 src/include/access/gin_private.h   |  1 +
 4 files changed, 97 insertions(+), 4 deletions(-)

diff --git a/src/backend/access/gin/gininsert.c b/src/backend/access/gin/gininsert.c
index 7c2f46b9541..7286432698e 100644
--- a/src/backend/access/gin/gininsert.c
+++ b/src/backend/access/gin/gininsert.c
@@ -21,6 +21,7 @@
 #include "access/xloginsert.h"
 #include "catalog/index.h"
 #include "catalog/pg_collation.h"
+#include "commands/progress.h"
 #include "commands/vacuum.h"
 #include "miscadmin.h"
 #include "nodes/execnodes.h"
@@ -644,6 +645,10 @@ ginbuild(Relation heap, Relation index, IndexInfo *indexInfo)
 	buildstate.accum.ginstate = &buildstate.ginstate;
 	ginInitBA(&buildstate.accum);
 
+	/* Report table scan phase started */
+	pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE,
+								 PROGRESS_GIN_PHASE_INDEXBUILD_TABLESCAN);
+
 	/*
 	 * Attempt to launch parallel worker scan when required
 	 *
@@ -1481,15 +1486,42 @@ _gin_parallel_merge(GinBuildState *state)
 	double		reltuples = 0;
 	GinBuffer  *buffer;
 
+	/* GIN tuples from workers, merged by leader */
+	double		numtuples = 0;
+
 	/* wait for workers to scan table and produce partial results */
 	reltuples = _gin_parallel_heapscan(state);
 
+	/* Execute the sort */
+	pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE,
+								 PROGRESS_GIN_PHASE_PERFORMSORT_2);
+
 	/* do the actual sort in the leader */
 	tuplesort_performsort(state->bs_sortstate);
 
 	/* initialize buffer to combine entries for the same key */
 	buffer = GinBufferInit(state->ginstate.index);
 
+	/*
+	 * Set the progress target for the next phase.  Reset the block number
+	 * values set by table_index_build_scan
+	 */
+	{
+		const int	progress_index[] = {
+			PROGRESS_CREATEIDX_SUBPHASE,
+			PROGRESS_CREATEIDX_TUPLES_TOTAL,
+			PROGRESS_SCAN_BLOCKS_TOTAL,
+			PROGRESS_SCAN_BLOCKS_DONE
+		};
+		const int64 progress_vals[] = {
+			PROGRESS_GIN_PHASE_MERGE_2,
+			state->bs_numtuples,
+			0, 0
+		};
+
+		pgstat_progress_update_multi_param(4, progress_index, progress_vals);
+	}
+
 	/*
 	 * Read the GIN tuples from the shared tuplesort, sorted by category and
 	 * key. That probably gives us order matching how data is organized in the
@@ -1530,6 +1562,10 @@ _gin_parallel_merge(GinBuildState *state)
 		 * or append if to the existing data).
 		 */
 		GinBufferStoreTuple(buffer, tup);
+
+		/* Report progress */
+		pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_DONE,
+									 ++numtuples);
 	}
 
 	/* flush data remaining in the buffer (for the last key) */
@@ -1543,6 +1579,10 @@ _gin_parallel_merge(GinBuildState *state)
 
 		/* discard the existing data */
 		GinBufferReset(buffer);
+
+		/* Report progress */
+		pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_DONE,
+									 ++numtuples);
 	}
 
 	/* relase all the memory */
@@ -1583,7 +1623,8 @@ _gin_leader_participate_as_worker(GinBuildState *buildstate, Relation heap, Rela
 
 	/* Perform work common to all participants */
 	_gin_parallel_scan_and_build(buildstate, ginleader->ginshared,
-								 ginleader->sharedsort, heap, index, sortmem, true);
+								 ginleader->sharedsort, heap, index,
+								 sortmem, true);
 }
 
 /*
@@ -1601,7 +1642,8 @@ _gin_leader_participate_as_worker(GinBuildState *buildstate, Relation heap, Rela
  * do a very limited number of mergesorts, which is good.
  */
 static void
-_gin_process_worker_data(GinBuildState *state, Tuplesortstate *worker_sort)
+_gin_process_worker_data(GinBuildState *state, Tuplesortstate *worker_sort,
+						 bool progress)
 {
 	GinTuple   *tup;
 	Size		tuplen;
@@ -1612,8 +1654,19 @@ _gin_process_worker_data(GinBuildState *state, Tuplesortstate *worker_sort)
 	buffer = GinBufferInit(state->ginstate.index);
 
 	/* sort the raw per-worker data */
+	if (progress)
+		pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE,
+									 PROGRESS_GIN_PHASE_PERFORMSORT_1);
+
 	tuplesort_performsort(state->bs_worker_sort);
 
+	/* reset the number of GIN tuples produced by this worker */
+	state->bs_numtuples = 0;
+
+	if (progress)
+		pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE,
+									 PROGRESS_GIN_PHASE_MERGE_1);
+
 	/*
 	 * Read the GIN tuples from the shared tuplesort, sorted by the key, and
 	 * merge them into larger chunks for the leader to combine.
@@ -1645,6 +1698,7 @@ _gin_process_worker_data(GinBuildState *state, Tuplesortstate *worker_sort)
 									buffer->items, buffer->nitems, &ntuplen);
 
 			tuplesort_putgintuple(state->bs_sortstate, ntup, ntuplen);
+			state->bs_numtuples++;
 
 			pfree(ntup);
 
@@ -1672,6 +1726,7 @@ _gin_process_worker_data(GinBuildState *state, Tuplesortstate *worker_sort)
 								buffer->items, buffer->nitems, &ntuplen);
 
 		tuplesort_putgintuple(state->bs_sortstate, ntup, ntuplen);
+		state->bs_numtuples++;
 
 		pfree(ntup);
 
@@ -1775,7 +1830,7 @@ _gin_parallel_scan_and_build(GinBuildState *state,
 	 * the callback, and combine them into much larger chunks and place that
 	 * into the shared tuplestore for leader to process.
 	 */
-	_gin_process_worker_data(state, state->bs_worker_sort);
+	_gin_process_worker_data(state, state->bs_worker_sort, progress);
 
 	/* sort the GIN tuples built by this worker */
 	tuplesort_performsort(state->bs_sortstate);
diff --git a/src/backend/access/gin/ginutil.c b/src/backend/access/gin/ginutil.c
index 6b2dd40fa0f..a61532538c0 100644
--- a/src/backend/access/gin/ginutil.c
+++ b/src/backend/access/gin/ginutil.c
@@ -20,6 +20,7 @@
 #include "access/xloginsert.h"
 #include "catalog/pg_collation.h"
 #include "catalog/pg_type.h"
+#include "commands/progress.h"
 #include "commands/vacuum.h"
 #include "miscadmin.h"
 #include "storage/indexfsm.h"
@@ -72,7 +73,7 @@ ginhandler(PG_FUNCTION_ARGS)
 	amroutine->amgettreeheight = NULL;
 	amroutine->amoptions = ginoptions;
 	amroutine->amproperty = NULL;
-	amroutine->ambuildphasename = NULL;
+	amroutine->ambuildphasename = ginbuildphasename;
 	amroutine->amvalidate = ginvalidate;
 	amroutine->amadjustmembers = ginadjustmembers;
 	amroutine->ambeginscan = ginbeginscan;
@@ -700,3 +701,28 @@ ginUpdateStats(Relation index, const GinStatsData *stats, bool is_build)
 
 	END_CRIT_SECTION();
 }
+
+/*
+ *	ginbuildphasename() -- Return name of index build phase.
+ */
+char *
+ginbuildphasename(int64 phasenum)
+{
+	switch (phasenum)
+	{
+		case PROGRESS_CREATEIDX_SUBPHASE_INITIALIZE:
+			return "initializing";
+		case PROGRESS_GIN_PHASE_INDEXBUILD_TABLESCAN:
+			return "scanning table";
+		case PROGRESS_GIN_PHASE_PERFORMSORT_1:
+			return "sorting tuples (workers)";
+		case PROGRESS_GIN_PHASE_MERGE_1:
+			return "merging tuples (workers)";
+		case PROGRESS_GIN_PHASE_PERFORMSORT_2:
+			return "sorting tuples";
+		case PROGRESS_GIN_PHASE_MERGE_2:
+			return "merging tuples";
+		default:
+			return NULL;
+	}
+}
diff --git a/src/include/access/gin.h b/src/include/access/gin.h
index 2debdac0f43..2e1076a0499 100644
--- a/src/include/access/gin.h
+++ b/src/include/access/gin.h
@@ -38,6 +38,17 @@
 #define GIN_SEARCH_MODE_ALL				2
 #define GIN_SEARCH_MODE_EVERYTHING		3	/* for internal use only */
 
+/*
+ * Constant definition for progress reporting.  Phase numbers must match
+ * ginbuildphasename.
+ */
+/* PROGRESS_CREATEIDX_SUBPHASE_INITIALIZE is 1 (see progress.h) */
+#define PROGRESS_GIN_PHASE_INDEXBUILD_TABLESCAN		2
+#define PROGRESS_GIN_PHASE_PERFORMSORT_1			3
+#define PROGRESS_GIN_PHASE_MERGE_1					4
+#define PROGRESS_GIN_PHASE_PERFORMSORT_2			5
+#define PROGRESS_GIN_PHASE_MERGE_2					6
+
 /*
  * GinStatsData represents stats data for planner use
  */
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 50478db9820..95d8805b66f 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -109,6 +109,7 @@ extern Datum *ginExtractEntries(GinState *ginstate, OffsetNumber attnum,
 extern OffsetNumber gintuple_get_attrnum(GinState *ginstate, IndexTuple tuple);
 extern Datum gintuple_get_key(GinState *ginstate, IndexTuple tuple,
 							  GinNullCategory *category);
+extern char *ginbuildphasename(int64 phasenum);
 
 /* gininsert.c */
 extern IndexBuildResult *ginbuild(Relation heap, Relation index,
-- 
2.48.1