v20250107-0005-Collect-and-print-compression-stats.patch

From ac5bb4302d74efb0d4a69a7bd623206ab5c30e70 Mon Sep 17 00:00:00 2001
From: Tomas Vondra <tomas.vondra@postgresql.org>
Date: Thu, 2 May 2024 15:21:43 +0200
Subject: [PATCH v20250107 05/10] Collect and print compression stats

Allows evaluating the benefits of compressing the TID lists.
---
 src/backend/access/gin/gininsert.c | 36 +++++++++++++++++++++++++-----
 src/include/access/gin.h           |  2 ++
 2 files changed, 32 insertions(+), 6 deletions(-)

diff --git a/src/backend/access/gin/gininsert.c b/src/backend/access/gin/gininsert.c
index 66f489abcab..1fc67ca1b8f 100644
--- a/src/backend/access/gin/gininsert.c
+++ b/src/backend/access/gin/gininsert.c
@@ -191,7 +191,8 @@ static void _gin_parallel_scan_and_build(GinBuildState *buildstate,
 static ItemPointer _gin_parse_tuple_items(GinTuple *a);
 static Datum _gin_parse_tuple_key(GinTuple *a);
 
-static GinTuple *_gin_build_tuple(OffsetNumber attrnum, unsigned char category,
+static GinTuple *_gin_build_tuple(GinBuildState *state,
+								  OffsetNumber attrnum, unsigned char category,
 								  Datum key, int16 typlen, bool typbyval,
 								  ItemPointerData *items, uint32 nitems,
 								  Size *len);
@@ -554,7 +555,7 @@ ginBuildCallbackParallel(Relation index, ItemPointer tid, Datum *values,
 			/* there could be many entries, so be willing to abort here */
 			CHECK_FOR_INTERRUPTS();
 
-			tup = _gin_build_tuple(attnum, category,
+			tup = _gin_build_tuple(buildstate, attnum, category,
 								   key, attr->attlen, attr->attbyval,
 								   list, nlist, &tuplen);
 
@@ -1642,6 +1643,15 @@ _gin_process_worker_data(GinBuildState *state, Tuplesortstate *worker_sort)
 	/* sort the raw per-worker data */
 	tuplesort_performsort(state->bs_worker_sort);
 
+	/* print some basic info */
+	elog(LOG, "_gin_parallel_scan_and_build raw %zu compressed %zu ratio %.2f%%",
+		 state->buildStats.sizeRaw, state->buildStats.sizeCompressed,
+		 (100.0 * state->buildStats.sizeCompressed) / state->buildStats.sizeRaw);
+
+	/* reset before the second phase */
+	state->buildStats.sizeCompressed = 0;
+	state->buildStats.sizeRaw = 0;
+
 	/*
 	 * Read the GIN tuples from the shared tuplesort, sorted by the key, and
 	 * merge them into larger chunks for the leader to combine.
@@ -1668,7 +1678,7 @@ _gin_process_worker_data(GinBuildState *state, Tuplesortstate *worker_sort)
 			 */
 			AssertCheckItemPointers(buffer, true);
 
-			ntup = _gin_build_tuple(buffer->attnum, buffer->category,
+			ntup = _gin_build_tuple(state, buffer->attnum, buffer->category,
 									buffer->key, buffer->typlen, buffer->typbyval,
 									buffer->items, buffer->nitems, &ntuplen);
 
@@ -1695,7 +1705,7 @@ _gin_process_worker_data(GinBuildState *state, Tuplesortstate *worker_sort)
 
 		AssertCheckItemPointers(buffer, true);
 
-		ntup = _gin_build_tuple(buffer->attnum, buffer->category,
+		ntup = _gin_build_tuple(state, buffer->attnum, buffer->category,
 								buffer->key, buffer->typlen, buffer->typbyval,
 								buffer->items, buffer->nitems, &ntuplen);
 
@@ -1710,6 +1720,11 @@ _gin_process_worker_data(GinBuildState *state, Tuplesortstate *worker_sort)
 	/* relase all the memory */
 	GinBufferFree(buffer);
 
+	/* print some basic info */
+	elog(LOG, "_gin_process_worker_data raw %zu compressed %zu ratio %.2f%%",
+		 state->buildStats.sizeRaw, state->buildStats.sizeCompressed,
+		 (100.0 * state->buildStats.sizeCompressed) / state->buildStats.sizeRaw);
+
 	tuplesort_end(worker_sort);
 }
 
@@ -1782,7 +1797,7 @@ _gin_parallel_scan_and_build(GinBuildState *state,
 			/* there could be many entries, so be willing to abort here */
 			CHECK_FOR_INTERRUPTS();
 
-			tup = _gin_build_tuple(attnum, category,
+			tup = _gin_build_tuple(state, attnum, category,
 								   key, attr->attlen, attr->attbyval,
 								   list, nlist, &len);
 
@@ -1876,6 +1891,7 @@ _gin_parallel_build_main(dsm_segment *seg, shm_toc *toc)
 	/* initialize the GIN build state */
 	initGinState(&buildstate.ginstate, indexRel);
 	buildstate.indtuples = 0;
+	/* XXX Shouldn't this initialize the other fields too, like ginbuild()? */
 	memset(&buildstate.buildStats, 0, sizeof(GinStatsData));
 
 	/*
@@ -1953,7 +1969,8 @@ typedef struct
  * of that into the GIN tuple.
  */
 static GinTuple *
-_gin_build_tuple(OffsetNumber attrnum, unsigned char category,
+_gin_build_tuple(GinBuildState *state,
+				 OffsetNumber attrnum, unsigned char category,
 				 Datum key, int16 typlen, bool typbyval,
 				 ItemPointerData *items, uint32 nitems,
 				 Size *len)
@@ -2087,6 +2104,13 @@ _gin_build_tuple(OffsetNumber attrnum, unsigned char category,
 		pfree(seginfo);
 	}
 
+	/* how large would the tuple be without compression? */
+	state->buildStats.sizeRaw += MAXALIGN(offsetof(GinTuple, data) + keylen) +
+		nitems * sizeof(ItemPointerData);
+
+	/* compressed size */
+	state->buildStats.sizeCompressed += tuplen;
+
 	return tuple;
 }
 
diff --git a/src/include/access/gin.h b/src/include/access/gin.h
index 2debdac0f43..c1938d0b9c6 100644
--- a/src/include/access/gin.h
+++ b/src/include/access/gin.h
@@ -49,6 +49,8 @@ typedef struct GinStatsData
 	BlockNumber nDataPages;
 	int64		nEntries;
 	int32		ginVersion;
+	Size		sizeRaw;
+	Size		sizeCompressed;
 } GinStatsData;
 
 /*
-- 
2.47.1