From a0416df1404a927fcf81499c4a54b4e045c4fc00 Mon Sep 17 00:00:00 2001
From: Tomas Vondra <tv@fuzzy.cz>
Date: Sun, 13 Sep 2020 12:12:47 +0200
Subject: [PATCH 3/8] Optimize allocations in bringetbitmap

The bringetbitmap function allocates memory for various purposes, which
may be quite expensive, depending on the number of scan keys. Instead of
allocating them separately, allocate one bit chunk of memory an carve it
into smaller pieces as needed - all the pieces have the same lifespan,
and it saves quite a bit of CPU and memory overhead.

Author: Tomas Vondra <tomas.vondra@2ndquadrant.com>
Discussion: https://postgr.es/m/c1138ead-7668-f0e1-0638-c3be3237e812@2ndquadrant.com
---
 src/backend/access/brin/brin.c | 62 +++++++++++++++++++++++++++-------
 1 file changed, 49 insertions(+), 13 deletions(-)

diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c
index 4dd29c7b10..470431010d 100644
--- a/src/backend/access/brin/brin.c
+++ b/src/backend/access/brin/brin.c
@@ -372,6 +372,9 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
 	int		   *nkeys,
 			   *nnullkeys;
 	int			keyno;
+	char	   *ptr;
+	Size		len;
+	char	   *tmp PG_USED_FOR_ASSERTS_ONLY;

 	opaque = (BrinOpaque *) scan->opaque;
 	bdesc = opaque->bo_bdesc;
@@ -397,11 +400,50 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
 	 * Make room for per-attribute lists of scan keys that we'll pass to the
 	 * consistent support procedure. We keep null and regular keys separate,
 	 * so that we can easily pass regular keys to the consistent function.
+	 *
+	 * To reduce the allocation overhead, we allocate one big chunk and then
+	 * carve it into smaller arrays ourselves. All the pieces have exactly
+	 * the same lifetime, so that's OK.
 	 */
-	keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts);
-	nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts);
-	nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts);
-	nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts);
+	len =
+		/* regular keys */
+		MAXALIGN(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts) +
+		MAXALIGN(sizeof(ScanKey) * scan->numberOfKeys * bdesc->bd_tupdesc->natts) +
+		MAXALIGN(sizeof(int) * bdesc->bd_tupdesc->natts) +
+		/* NULL keys */
+		MAXALIGN(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts) +
+		MAXALIGN(sizeof(ScanKey) * scan->numberOfKeys * bdesc->bd_tupdesc->natts) +
+		MAXALIGN(sizeof(int) * bdesc->bd_tupdesc->natts);
+
+	ptr = palloc(len);
+	tmp = ptr;
+
+	keys = (ScanKey **) ptr;
+	ptr += MAXALIGN(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts);
+
+	nullkeys = (ScanKey **) ptr;
+	ptr += MAXALIGN(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts);
+
+	nkeys = (int *) ptr;
+	ptr += MAXALIGN(sizeof(int) * bdesc->bd_tupdesc->natts);
+
+	nnullkeys = (int *) ptr;
+	ptr += MAXALIGN(sizeof(int) * bdesc->bd_tupdesc->natts);
+
+	for (int i = 0; i < bdesc->bd_tupdesc->natts; i++)
+	{
+		keys[i] = (ScanKey *) ptr;
+		ptr += MAXALIGN(sizeof(ScanKey) * scan->numberOfKeys);
+
+		nullkeys[i] = (ScanKey *) ptr;
+		ptr += MAXALIGN(sizeof(ScanKey) * scan->numberOfKeys);
+	}
+
+	Assert(tmp + len == ptr);
+
+	/* zero the number of keys */
+	memset(nkeys, 0, sizeof(int) * bdesc->bd_tupdesc->natts);
+	memset(nnullkeys, 0, sizeof(int) * bdesc->bd_tupdesc->natts);

 	/*
 	 * Preprocess the scan keys - split them into per-attribute arrays.
@@ -437,9 +479,9 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
 		{
 			FmgrInfo   *tmp;

-			/* No key/null arrays for this attribute. */
-			Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0));
-			Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0));
+			/* First time we see this attribute, so no key/null keys. */
+			Assert(nkeys[keyattno - 1] == 0);
+			Assert(nnullkeys[keyattno - 1] == 0);

 			tmp = index_getprocinfo(idxRel, keyattno,
 									BRIN_PROCNUM_CONSISTENT);
@@ -450,17 +492,11 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
 		/* Add key to the proper per-attribute array. */
 		if (key->sk_flags & SK_ISNULL)
 		{
-			if (!nullkeys[keyattno - 1])
-				nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys);
-
 			nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key;
 			nnullkeys[keyattno - 1]++;
 		}
 		else
 		{
-			if (!keys[keyattno - 1])
-				keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys);
-
 			keys[keyattno - 1][nkeys[keyattno - 1]] = key;
 			nkeys[keyattno - 1]++;
 		}
-- 
2.26.2