Heikki Linnakangas ccadf73163 Use the buffer cache when initializing an unlogged index.
Some of the ambuildempty functions used smgrwrite() directly, followed
by smgrimmedsync(). A few small problems with that:

Firstly, one is supposed to use smgrextend() when extending a
relation, not smgrwrite(). It doesn't make much difference in
production builds. smgrextend() updates the relation size cache, so
you miss that, but that's harmless because we never use the cached
relation size of an init fork. But if you compile with
CHECK_WRITE_VS_EXTEND, you get an assertion failure.

Secondly, the smgrwrite() calls were performed before WAL-logging, so
the page image written to disk had 0/0 as the LSN, not the LSN of the
WAL record. That's also harmless in practice, but seems sloppy.

Thirdly, it's better to use the buffer cache, because then you don't
need to smgrimmedsync() the relation to disk, which adds latency.
Bypassing the cache makes sense for bulk operations like index
creation, but not when you're just initializing an empty index.
Creation of unlogged tables is hardly performance bottleneck in any
real world applications, but nevertheless.

Backpatch to v16, but no further. These issues should be harmless in
practice, so better to not rock the boat in older branches.

Reviewed-by: Robert Haas
Discussion: https://www.postgresql.org/message-id/6e5bbc08-cdfc-b2b3-9e23-1a914b9850a9@iki.fi
2023-08-23 17:21:31 +03:00

237 lines
6.4 KiB
C

/*-------------------------------------------------------------------------
*
* spginsert.c
* Externally visible index creation/insertion routines
*
* All the actual insertion logic is in spgdoinsert.c.
*
* Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
* src/backend/access/spgist/spginsert.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "access/genam.h"
#include "access/spgist_private.h"
#include "access/spgxlog.h"
#include "access/tableam.h"
#include "access/xlog.h"
#include "access/xloginsert.h"
#include "catalog/index.h"
#include "miscadmin.h"
#include "storage/bufmgr.h"
#include "storage/smgr.h"
#include "utils/memutils.h"
#include "utils/rel.h"
typedef struct
{
SpGistState spgstate; /* SPGiST's working state */
int64 indtuples; /* total number of tuples indexed */
MemoryContext tmpCtx; /* per-tuple temporary context */
} SpGistBuildState;
/* Callback to process one heap tuple during table_index_build_scan */
static void
spgistBuildCallback(Relation index, ItemPointer tid, Datum *values,
bool *isnull, bool tupleIsAlive, void *state)
{
SpGistBuildState *buildstate = (SpGistBuildState *) state;
MemoryContext oldCtx;
/* Work in temp context, and reset it after each tuple */
oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);
/*
* Even though no concurrent insertions can be happening, we still might
* get a buffer-locking failure due to bgwriter or checkpointer taking a
* lock on some buffer. So we need to be willing to retry. We can flush
* any temp data when retrying.
*/
while (!spgdoinsert(index, &buildstate->spgstate, tid,
values, isnull))
{
MemoryContextReset(buildstate->tmpCtx);
}
/* Update total tuple count */
buildstate->indtuples += 1;
MemoryContextSwitchTo(oldCtx);
MemoryContextReset(buildstate->tmpCtx);
}
/*
* Build an SP-GiST index.
*/
IndexBuildResult *
spgbuild(Relation heap, Relation index, IndexInfo *indexInfo)
{
IndexBuildResult *result;
double reltuples;
SpGistBuildState buildstate;
Buffer metabuffer,
rootbuffer,
nullbuffer;
if (RelationGetNumberOfBlocks(index) != 0)
elog(ERROR, "index \"%s\" already contains data",
RelationGetRelationName(index));
/*
* Initialize the meta page and root pages
*/
metabuffer = SpGistNewBuffer(index);
rootbuffer = SpGistNewBuffer(index);
nullbuffer = SpGistNewBuffer(index);
Assert(BufferGetBlockNumber(metabuffer) == SPGIST_METAPAGE_BLKNO);
Assert(BufferGetBlockNumber(rootbuffer) == SPGIST_ROOT_BLKNO);
Assert(BufferGetBlockNumber(nullbuffer) == SPGIST_NULL_BLKNO);
START_CRIT_SECTION();
SpGistInitMetapage(BufferGetPage(metabuffer));
MarkBufferDirty(metabuffer);
SpGistInitBuffer(rootbuffer, SPGIST_LEAF);
MarkBufferDirty(rootbuffer);
SpGistInitBuffer(nullbuffer, SPGIST_LEAF | SPGIST_NULLS);
MarkBufferDirty(nullbuffer);
END_CRIT_SECTION();
UnlockReleaseBuffer(metabuffer);
UnlockReleaseBuffer(rootbuffer);
UnlockReleaseBuffer(nullbuffer);
/*
* Now insert all the heap data into the index
*/
initSpGistState(&buildstate.spgstate, index);
buildstate.spgstate.isBuild = true;
buildstate.indtuples = 0;
buildstate.tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
"SP-GiST build temporary context",
ALLOCSET_DEFAULT_SIZES);
reltuples = table_index_build_scan(heap, index, indexInfo, true, true,
spgistBuildCallback, (void *) &buildstate,
NULL);
MemoryContextDelete(buildstate.tmpCtx);
SpGistUpdateMetaPage(index);
/*
* We didn't write WAL records as we built the index, so if WAL-logging is
* required, write all pages to the WAL now.
*/
if (RelationNeedsWAL(index))
{
log_newpage_range(index, MAIN_FORKNUM,
0, RelationGetNumberOfBlocks(index),
true);
}
result = (IndexBuildResult *) palloc0(sizeof(IndexBuildResult));
result->heap_tuples = reltuples;
result->index_tuples = buildstate.indtuples;
return result;
}
/*
* Build an empty SPGiST index in the initialization fork
*/
void
spgbuildempty(Relation index)
{
Buffer metabuffer,
rootbuffer,
nullbuffer;
/*
* Initialize the meta page and root pages
*/
metabuffer = ReadBufferExtended(index, INIT_FORKNUM, P_NEW, RBM_NORMAL, NULL);
LockBuffer(metabuffer, BUFFER_LOCK_EXCLUSIVE);
rootbuffer = ReadBufferExtended(index, INIT_FORKNUM, P_NEW, RBM_NORMAL, NULL);
LockBuffer(rootbuffer, BUFFER_LOCK_EXCLUSIVE);
nullbuffer = ReadBufferExtended(index, INIT_FORKNUM, P_NEW, RBM_NORMAL, NULL);
LockBuffer(nullbuffer, BUFFER_LOCK_EXCLUSIVE);
Assert(BufferGetBlockNumber(metabuffer) == SPGIST_METAPAGE_BLKNO);
Assert(BufferGetBlockNumber(rootbuffer) == SPGIST_ROOT_BLKNO);
Assert(BufferGetBlockNumber(nullbuffer) == SPGIST_NULL_BLKNO);
START_CRIT_SECTION();
SpGistInitMetapage(BufferGetPage(metabuffer));
MarkBufferDirty(metabuffer);
SpGistInitBuffer(rootbuffer, SPGIST_LEAF);
MarkBufferDirty(rootbuffer);
SpGistInitBuffer(nullbuffer, SPGIST_LEAF | SPGIST_NULLS);
MarkBufferDirty(nullbuffer);
log_newpage_buffer(metabuffer, true);
log_newpage_buffer(rootbuffer, true);
log_newpage_buffer(nullbuffer, true);
END_CRIT_SECTION();
UnlockReleaseBuffer(metabuffer);
UnlockReleaseBuffer(rootbuffer);
UnlockReleaseBuffer(nullbuffer);
}
/*
* Insert one new tuple into an SPGiST index.
*/
bool
spginsert(Relation index, Datum *values, bool *isnull,
ItemPointer ht_ctid, Relation heapRel,
IndexUniqueCheck checkUnique,
bool indexUnchanged,
IndexInfo *indexInfo)
{
SpGistState spgstate;
MemoryContext oldCtx;
MemoryContext insertCtx;
insertCtx = AllocSetContextCreate(CurrentMemoryContext,
"SP-GiST insert temporary context",
ALLOCSET_DEFAULT_SIZES);
oldCtx = MemoryContextSwitchTo(insertCtx);
initSpGistState(&spgstate, index);
/*
* We might have to repeat spgdoinsert() multiple times, if conflicts
* occur with concurrent insertions. If so, reset the insertCtx each time
* to avoid cumulative memory consumption. That means we also have to
* redo initSpGistState(), but it's cheap enough not to matter.
*/
while (!spgdoinsert(index, &spgstate, ht_ctid, values, isnull))
{
MemoryContextReset(insertCtx);
initSpGistState(&spgstate, index);
}
SpGistUpdateMetaPage(index);
MemoryContextSwitchTo(oldCtx);
MemoryContextDelete(insertCtx);
/* return false since we've not done any unique check */
return false;
}