public inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v12 12/17] Hard-code TBMIterateResult offsets array size
20+ messages / 3 participants
[nested] [flat]

* [PATCH v12 12/17] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 33 +++++++--------------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 28 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fcc..1dc4c99bf99 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1463,12 +1449,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	TBMSharedIterator *iterator;
 	TBMSharedIteratorState *istate;
 
-	/*
-	 * Create the TBMSharedIterator struct, with enough trailing space to
-	 * serve the needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639bf..432fae52962 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--6jpz2j246qmht4bt
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v12-0013-Separate-TBM-Shared-Iterator-and-TBMIterateResul.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* [PATCH v9 11/17] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 33 +++++++--------------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 28 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fc..1dc4c99bf9 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1463,12 +1449,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	TBMSharedIterator *iterator;
 	TBMSharedIteratorState *istate;
 
-	/*
-	 * Create the TBMSharedIterator struct, with enough trailing space to
-	 * serve the needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639b..432fae5296 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--7mdtsjmrzitrgzgx
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v9-0012-Separate-TBM-Shared-Iterator-and-TBMIterateResult.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* [PATCH v10 12/17] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 33 +++++++--------------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 28 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fc..1dc4c99bf9 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1463,12 +1449,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	TBMSharedIterator *iterator;
 	TBMSharedIteratorState *istate;
 
-	/*
-	 * Create the TBMSharedIterator struct, with enough trailing space to
-	 * serve the needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639b..432fae5296 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--3o7pc6dfau5a5hry
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v10-0013-Separate-TBM-Shared-Iterator-and-TBMIterateResul.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* [PATCH v11 12/17] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 33 +++++++--------------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 28 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fc..1dc4c99bf9 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1463,12 +1449,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	TBMSharedIterator *iterator;
 	TBMSharedIteratorState *istate;
 
-	/*
-	 * Create the TBMSharedIterator struct, with enough trailing space to
-	 * serve the needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639b..432fae5296 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--owzzsiozz6hgpp7e
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v11-0013-Separate-TBM-Shared-Iterator-and-TBMIterateResul.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* [PATCH v6 11/14] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 29 +++++++----------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 24 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fcc..d2bf8f44d50 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1467,8 +1453,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	 * Create the TBMSharedIterator struct, with enough trailing space to
 	 * serve the needs of the TBMIterateResult sub-struct.
 	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639bf..432fae52962 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--w4wcjcocxsm37usi
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v6-0012-Separate-TBM-Shared-Iterator-and-TBMIterateResult.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* [PATCH v7 10/13] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 29 +++++++----------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 24 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fcc..d2bf8f44d50 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1467,8 +1453,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	 * Create the TBMSharedIterator struct, with enough trailing space to
 	 * serve the needs of the TBMIterateResult sub-struct.
 	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639bf..432fae52962 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--kqqpqghcwbcc3dt5
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v7-0011-Separate-TBM-Shared-Iterator-and-TBMIterateResult.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* [PATCH v8 10/17] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 33 +++++++--------------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 28 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fc..1dc4c99bf9 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1463,12 +1449,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	TBMSharedIterator *iterator;
 	TBMSharedIteratorState *istate;
 
-	/*
-	 * Create the TBMSharedIterator struct, with enough trailing space to
-	 * serve the needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639b..432fae5296 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--xqq4defy3uncu6k6
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v8-0011-table_scan_bitmap_next_block-counts-lossy-and-exa.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* [PATCH v9 11/17] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 33 +++++++--------------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 28 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fc..1dc4c99bf9 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1463,12 +1449,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	TBMSharedIterator *iterator;
 	TBMSharedIteratorState *istate;
 
-	/*
-	 * Create the TBMSharedIterator struct, with enough trailing space to
-	 * serve the needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639b..432fae5296 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--7mdtsjmrzitrgzgx
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v9-0012-Separate-TBM-Shared-Iterator-and-TBMIterateResult.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* [PATCH v10 12/17] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 33 +++++++--------------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 28 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fc..1dc4c99bf9 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1463,12 +1449,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	TBMSharedIterator *iterator;
 	TBMSharedIteratorState *istate;
 
-	/*
-	 * Create the TBMSharedIterator struct, with enough trailing space to
-	 * serve the needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639b..432fae5296 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--3o7pc6dfau5a5hry
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v10-0013-Separate-TBM-Shared-Iterator-and-TBMIterateResul.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* [PATCH v11 12/17] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 33 +++++++--------------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 28 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fc..1dc4c99bf9 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1463,12 +1449,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	TBMSharedIterator *iterator;
 	TBMSharedIteratorState *istate;
 
-	/*
-	 * Create the TBMSharedIterator struct, with enough trailing space to
-	 * serve the needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639b..432fae5296 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--owzzsiozz6hgpp7e
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v11-0013-Separate-TBM-Shared-Iterator-and-TBMIterateResul.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* [PATCH v6 11/14] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 29 +++++++----------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 24 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fcc..d2bf8f44d50 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1467,8 +1453,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	 * Create the TBMSharedIterator struct, with enough trailing space to
 	 * serve the needs of the TBMIterateResult sub-struct.
 	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639bf..432fae52962 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--w4wcjcocxsm37usi
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v6-0012-Separate-TBM-Shared-Iterator-and-TBMIterateResult.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* [PATCH v7 10/13] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 29 +++++++----------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 24 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fcc..d2bf8f44d50 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1467,8 +1453,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	 * Create the TBMSharedIterator struct, with enough trailing space to
 	 * serve the needs of the TBMIterateResult sub-struct.
 	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639bf..432fae52962 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--kqqpqghcwbcc3dt5
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v7-0011-Separate-TBM-Shared-Iterator-and-TBMIterateResult.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* [PATCH v8 10/17] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 33 +++++++--------------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 28 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fc..1dc4c99bf9 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1463,12 +1449,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	TBMSharedIterator *iterator;
 	TBMSharedIteratorState *istate;
 
-	/*
-	 * Create the TBMSharedIterator struct, with enough trailing space to
-	 * serve the needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639b..432fae5296 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--xqq4defy3uncu6k6
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v8-0011-table_scan_bitmap_next_block-counts-lossy-and-exa.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* [PATCH v9 11/17] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 33 +++++++--------------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 28 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fc..1dc4c99bf9 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1463,12 +1449,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	TBMSharedIterator *iterator;
 	TBMSharedIteratorState *istate;
 
-	/*
-	 * Create the TBMSharedIterator struct, with enough trailing space to
-	 * serve the needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639b..432fae5296 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--7mdtsjmrzitrgzgx
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v9-0012-Separate-TBM-Shared-Iterator-and-TBMIterateResult.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* [PATCH v6 11/14] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 29 +++++++----------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 24 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fcc..d2bf8f44d50 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1467,8 +1453,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	 * Create the TBMSharedIterator struct, with enough trailing space to
 	 * serve the needs of the TBMIterateResult sub-struct.
 	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639bf..432fae52962 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--w4wcjcocxsm37usi
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v6-0012-Separate-TBM-Shared-Iterator-and-TBMIterateResult.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* [PATCH v7 10/13] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 29 +++++++----------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 24 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fcc..d2bf8f44d50 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1467,8 +1453,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	 * Create the TBMSharedIterator struct, with enough trailing space to
 	 * serve the needs of the TBMIterateResult sub-struct.
 	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639bf..432fae52962 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--kqqpqghcwbcc3dt5
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v7-0011-Separate-TBM-Shared-Iterator-and-TBMIterateResult.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* [PATCH v8 10/17] Hard-code TBMIterateResult offsets array size
@ 2024-02-16 01:13  Melanie Plageman <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Melanie Plageman @ 2024-02-16 01:13 UTC (permalink / raw)

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 33 +++++++--------------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 28 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index e8ab5d78fc..1dc4c99bf9 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -692,12 +683,7 @@ tbm_begin_iterate(TIDBitmap *tbm)
 
 	Assert(tbm->iterating != TBM_ITERATING_SHARED);
 
-	/*
-	 * Create the TBMIterator struct, with enough trailing space to serve the
-	 * needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMIterator *) palloc(sizeof(TBMIterator) +
-									  MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = palloc(sizeof(TBMIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1463,12 +1449,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	TBMSharedIterator *iterator;
 	TBMSharedIteratorState *istate;
 
-	/*
-	 * Create the TBMSharedIterator struct, with enough trailing space to
-	 * serve the needs of the TBMIterateResult sub-struct.
-	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index 1945f0639b..432fae5296 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -41,9 +42,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.40.1


--xqq4defy3uncu6k6
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v8-0011-table_scan_bitmap_next_block-counts-lossy-and-exa.patch"



^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* Re: Conflict detection and logging in logical replication
@ 2024-07-26 06:26  Amit Kapila <[email protected]>
  0 siblings, 1 reply; 20+ messages in thread

From: Amit Kapila @ 2024-07-26 06:26 UTC (permalink / raw)
  To: shveta malik <[email protected]>; +Cc: Zhijie Hou (Fujitsu) <[email protected]>; Nisha Moond <[email protected]>; pgsql-hackers; Dilip Kumar <[email protected]>; Jan Wieck <[email protected]>; Tomas Vondra <[email protected]>; Ashutosh Bapat <[email protected]>

On Fri, Jul 26, 2024 at 9:39 AM shveta malik <[email protected]> wrote:
>
> On Thu, Jul 11, 2024 at 7:47 AM Zhijie Hou (Fujitsu)
> <[email protected]> wrote:
> >
> > On Wednesday, July 10, 2024 5:39 PM shveta malik <[email protected]> wrote:
> > >
>
> > > 2)
> > > Another case which might confuse user:
> > >
> > > CREATE TABLE t1 (pk integer primary key, val1 integer, val2 integer);
> > >
> > > On PUB: insert into t1 values(1,10,10); insert into t1 values(2,20,20);
> > >
> > > On SUB: update t1 set pk=3 where pk=2;
> > >
> > > Data on PUB: {1,10,10}, {2,20,20}
> > > Data on SUB: {1,10,10}, {3,20,20}
> > >
> > > Now on PUB: update t1 set val1=200 where val1=20;
> > >
> > > On Sub, I get this:
> > > 2024-07-10 14:44:00.160 IST [648287] LOG:  conflict update_missing detected
> > > on relation "public.t1"
> > > 2024-07-10 14:44:00.160 IST [648287] DETAIL:  Did not find the row to be
> > > updated.
> > > 2024-07-10 14:44:00.160 IST [648287] CONTEXT:  processing remote data for
> > > replication origin "pg_16389" during message type "UPDATE" for replication
> > > target relation "public.t1" in transaction 760, finished at 0/156D658
> > >
> > > To user, it could be quite confusing, as val1=20 exists on sub but still he gets
> > > update_missing conflict and the 'DETAIL' is not sufficient to give the clarity. I
> > > think on HEAD as well (have not tested), we will get same behavior i.e. update
> > > will be ignored as we make search based on RI (pk in this case). So we are not
> > > worsening the situation, but now since we are detecting conflict, is it possible
> > > to give better details in 'DETAIL' section indicating what is actually missing?
> >
> > I think It's doable to report the row value that cannot be found in the local
> > relation, but the concern is the potential risk of exposing some
> > sensitive data in the log. This may be OK, as we are already reporting the
> > key value for constraints violation, so if others also agree, we can add
> > the row value in the DETAIL as well.
>
> This is still awaiting some feedback. I feel it will be good to add
> some pk value at-least in DETAIL section, like we add for other
> conflict types.
>

I agree that displaying pk where applicable should be okay as we
display it at other places but the same won't be possible when we do
sequence scan to fetch the required tuple. So, the message will be
different in that case, right?

-- 
With Regards,
Amit Kapila.






^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* RE: Conflict detection and logging in logical replication
@ 2024-08-04 07:34  Zhijie Hou (Fujitsu) <[email protected]>
  parent: Amit Kapila <[email protected]>
  0 siblings, 1 reply; 20+ messages in thread

From: Zhijie Hou (Fujitsu) @ 2024-08-04 07:34 UTC (permalink / raw)
  To: Amit Kapila <[email protected]>; shveta malik <[email protected]>; +Cc: Nisha Moond <[email protected]>; pgsql-hackers; Dilip Kumar <[email protected]>; Jan Wieck <[email protected]>; Tomas Vondra <[email protected]>; Ashutosh Bapat <[email protected]>

On Friday, July 26, 2024 2:26 PM Amit Kapila <[email protected]> wrote:
> 
> On Fri, Jul 26, 2024 at 9:39 AM shveta malik <[email protected]> wrote:
> >
> > On Thu, Jul 11, 2024 at 7:47 AM Zhijie Hou (Fujitsu)
> > <[email protected]> wrote:
> > >
> > > On Wednesday, July 10, 2024 5:39 PM shveta malik
> <[email protected]> wrote:
> > > >
> >
> > > > 2)
> > > > Another case which might confuse user:
> > > >
> > > > CREATE TABLE t1 (pk integer primary key, val1 integer, val2
> > > > integer);
> > > >
> > > > On PUB: insert into t1 values(1,10,10); insert into t1
> > > > values(2,20,20);
> > > >
> > > > On SUB: update t1 set pk=3 where pk=2;
> > > >
> > > > Data on PUB: {1,10,10}, {2,20,20}
> > > > Data on SUB: {1,10,10}, {3,20,20}
> > > >
> > > > Now on PUB: update t1 set val1=200 where val1=20;
> > > >
> > > > On Sub, I get this:
> > > > 2024-07-10 14:44:00.160 IST [648287] LOG:  conflict update_missing
> > > > detected on relation "public.t1"
> > > > 2024-07-10 14:44:00.160 IST [648287] DETAIL:  Did not find the row
> > > > to be updated.
> > > > 2024-07-10 14:44:00.160 IST [648287] CONTEXT:  processing remote
> > > > data for replication origin "pg_16389" during message type
> > > > "UPDATE" for replication target relation "public.t1" in
> > > > transaction 760, finished at 0/156D658
> > > >
> > > > To user, it could be quite confusing, as val1=20 exists on sub but
> > > > still he gets update_missing conflict and the 'DETAIL' is not
> > > > sufficient to give the clarity. I think on HEAD as well (have not
> > > > tested), we will get same behavior i.e. update will be ignored as
> > > > we make search based on RI (pk in this case). So we are not
> > > > worsening the situation, but now since we are detecting conflict, is it
> possible to give better details in 'DETAIL' section indicating what is actually
> missing?
> > >
> > > I think It's doable to report the row value that cannot be found in
> > > the local relation, but the concern is the potential risk of
> > > exposing some sensitive data in the log. This may be OK, as we are
> > > already reporting the key value for constraints violation, so if
> > > others also agree, we can add the row value in the DETAIL as well.
> >
> > This is still awaiting some feedback. I feel it will be good to add
> > some pk value at-least in DETAIL section, like we add for other
> > conflict types.
> >
> 
> I agree that displaying pk where applicable should be okay as we display it at
> other places but the same won't be possible when we do sequence scan to
> fetch the required tuple. So, the message will be different in that case, right?

After some research, I think we can report the key values in DETAIL if the
apply worker uses any unique indexes to find the tuple to update/delete.
Otherwise, we can try to output all column values in DETAIL if the current user
of apply worker has SELECT access to these columns.

This is consistent with what we do when reporting table constraint violation
(e.g. when violating a check constraint, it could output all the column value
if the current has access to all the column):

- First, use super user to create a table.
CREATE TABLE t1 (c1 int, c2 int, c3 int check (c3 < 5));

- 1) using super user to insert a row that violates the constraint. We should
see all the column value.

INSERT INTO t1(c3) VALUES (6);
	ERROR:  new row for relation "t1" violates check constraint "t1_c3_check"
	DETAIL:  Failing row contains (null, null, 6).

- 2) use a user without access to all the columns. We can only see the inserted column and 
CREATE USER regress_priv_user2;
GRANT INSERT (c1, c2, c3) ON t1 TO regress_priv_user2;

SET SESSION AUTHORIZATION regress_priv_user2;
INSERT INTO t1 (c3) VALUES (6);

	ERROR:  new row for relation "t1" violates check constraint "t1_c3_check"
	DETAIL:  Failing row contains (c3) = (6).

To achieve this, I think we can expose the ExecBuildSlotValueDescription
function and use it in conflict reporting. What do you think ?

Best Regards,
Hou zj


^ permalink  raw  reply  [nested|flat] 20+ messages in thread

* Re: Conflict detection and logging in logical replication
@ 2024-08-05 04:20  Amit Kapila <[email protected]>
  parent: Zhijie Hou (Fujitsu) <[email protected]>
  0 siblings, 0 replies; 20+ messages in thread

From: Amit Kapila @ 2024-08-05 04:20 UTC (permalink / raw)
  To: Zhijie Hou (Fujitsu) <[email protected]>; +Cc: shveta malik <[email protected]>; Nisha Moond <[email protected]>; pgsql-hackers; Dilip Kumar <[email protected]>; Jan Wieck <[email protected]>; Tomas Vondra <[email protected]>; Ashutosh Bapat <[email protected]>

On Sun, Aug 4, 2024 at 1:04 PM Zhijie Hou (Fujitsu)
<[email protected]> wrote:
>
> On Friday, July 26, 2024 2:26 PM Amit Kapila <[email protected]> wrote:
> >
> >
> > I agree that displaying pk where applicable should be okay as we display it at
> > other places but the same won't be possible when we do sequence scan to
> > fetch the required tuple. So, the message will be different in that case, right?
>
> After some research, I think we can report the key values in DETAIL if the
> apply worker uses any unique indexes to find the tuple to update/delete.
> Otherwise, we can try to output all column values in DETAIL if the current user
> of apply worker has SELECT access to these columns.
>

I don't see any problem with displaying the column values in the LOG
message when the user can access it. Also, we do the same in other
places to further strengthen this idea.

> This is consistent with what we do when reporting table constraint violation
> (e.g. when violating a check constraint, it could output all the column value
> if the current has access to all the column):
>
> - First, use super user to create a table.
> CREATE TABLE t1 (c1 int, c2 int, c3 int check (c3 < 5));
>
> - 1) using super user to insert a row that violates the constraint. We should
> see all the column value.
>
> INSERT INTO t1(c3) VALUES (6);
>         ERROR:  new row for relation "t1" violates check constraint "t1_c3_check"
>         DETAIL:  Failing row contains (null, null, 6).
>
> - 2) use a user without access to all the columns. We can only see the inserted column and
> CREATE USER regress_priv_user2;
> GRANT INSERT (c1, c2, c3) ON t1 TO regress_priv_user2;
>
> SET SESSION AUTHORIZATION regress_priv_user2;
> INSERT INTO t1 (c3) VALUES (6);
>
>         ERROR:  new row for relation "t1" violates check constraint "t1_c3_check"
>         DETAIL:  Failing row contains (c3) = (6).
>
> To achieve this, I think we can expose the ExecBuildSlotValueDescription
> function and use it in conflict reporting. What do you think ?
>

Agreed. We should also consider displaying both the local and remote
rows in case of update/delete_differ conflicts. Do, we have any case
during conflict reporting where we won't have access to any of the
columns? If so, we need to see what to display in such a case.

-- 
With Regards,
Amit Kapila.






^ permalink  raw  reply  [nested|flat] 20+ messages in thread

end of thread, other threads:[~2024-08-05 04:20 UTC | newest]

Thread overview: 20+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2024-02-16 01:13 [PATCH v12 12/17] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-02-16 01:13 [PATCH v11 12/17] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-02-16 01:13 [PATCH v9 11/17] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-02-16 01:13 [PATCH v7 10/13] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-02-16 01:13 [PATCH v9 11/17] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-02-16 01:13 [PATCH v10 12/17] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-02-16 01:13 [PATCH v11 12/17] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-02-16 01:13 [PATCH v6 11/14] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-02-16 01:13 [PATCH v8 10/17] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-02-16 01:13 [PATCH v7 10/13] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-02-16 01:13 [PATCH v10 12/17] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-02-16 01:13 [PATCH v6 11/14] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-02-16 01:13 [PATCH v7 10/13] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-02-16 01:13 [PATCH v8 10/17] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-02-16 01:13 [PATCH v9 11/17] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-02-16 01:13 [PATCH v6 11/14] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-02-16 01:13 [PATCH v8 10/17] Hard-code TBMIterateResult offsets array size Melanie Plageman <[email protected]>
2024-07-26 06:26 Re: Conflict detection and logging in logical replication Amit Kapila <[email protected]>
2024-08-04 07:34 ` RE: Conflict detection and logging in logical replication Zhijie Hou (Fujitsu) <[email protected]>
2024-08-05 04:20   ` Re: Conflict detection and logging in logical replication Amit Kapila <[email protected]>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox