mirror of
https://github.com/postgres/postgres.git
synced 2025-08-18 12:22:09 +03:00
23c743b645
RelationTruncate() does three things, while holding an
AccessExclusiveLock and preventing checkpoints:
1. Logs the truncation.
2. Drops buffers, even if they're dirty.
3. Truncates some number of files.
Step 2 could previously be canceled if it had to wait for I/O, and step
3 could and still can fail in file APIs. All orderings of these
operations have data corruption hazards if interrupted, so we can't give
up until the whole operation is done. When dirty pages were discarded
but the corresponding blocks were left on disk due to ERROR, old page
versions could come back from disk, reviving deleted data (see
pgsql-bugs #18146 and several like it). When primary and standby were
allowed to disagree on relation size, standbys could panic (see
pgsql-bugs #18426) or revive data unknown to visibility management on
the primary (theorized).
Changes:
* WAL is now unconditionally flushed first
* smgrtruncate() is now called in a critical section, preventing
interrupts and causing PANIC on file API failure
* smgrtruncate() has a new parameter for existing fork sizes,
because it can't call smgrnblocks() itself inside a critical section
The changes apply to RelationTruncate(), smgr_redo() and
pg_truncate_visibility_map(). That last is also brought up to date with
other evolutions of the truncation protocol.
The VACUUM FileTruncate() failure mode had been discussed in older
reports than the ones referenced below, with independent analysis from
many people, but earlier theories on how to fix it were too complicated
to back-patch. The more recently invented cancellation bug was
diagnosed by Alexander Lakhin. Other corruption scenarios were spotted
by me while iterating on this patch and earlier commit 75818b3a.
Back-patch to all supported releases.
Reviewed-by: Michael Paquier <michael@paquier.xyz>
Reviewed-by: Robert Haas <robertmhaas@gmail.com>
Reported-by: rootcause000@gmail.com
Reported-by: Alexander Lakhin <exclusion@gmail.com>
Discussion: https://postgr.es/m/18146-04e908c662113ad5%40postgresql.org
Discussion: https://postgr.es/m/18426-2d18da6586f152d6%40postgresql.org
53 lines
2.1 KiB
C
53 lines
2.1 KiB
C
/*-------------------------------------------------------------------------
|
|
*
|
|
* md.h
|
|
* magnetic disk storage manager public interface declarations.
|
|
*
|
|
*
|
|
* Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group
|
|
* Portions Copyright (c) 1994, Regents of the University of California
|
|
*
|
|
* src/include/storage/md.h
|
|
*
|
|
*-------------------------------------------------------------------------
|
|
*/
|
|
#ifndef MD_H
|
|
#define MD_H
|
|
|
|
#include "storage/block.h"
|
|
#include "storage/relfilenode.h"
|
|
#include "storage/smgr.h"
|
|
#include "storage/sync.h"
|
|
|
|
/* md storage manager functionality */
|
|
extern void mdinit(void);
|
|
extern void mdopen(SMgrRelation reln);
|
|
extern void mdclose(SMgrRelation reln, ForkNumber forknum);
|
|
extern void mdcreate(SMgrRelation reln, ForkNumber forknum, bool isRedo);
|
|
extern bool mdexists(SMgrRelation reln, ForkNumber forknum);
|
|
extern void mdunlink(RelFileNodeBackend rnode, ForkNumber forknum, bool isRedo);
|
|
extern void mdextend(SMgrRelation reln, ForkNumber forknum,
|
|
BlockNumber blocknum, char *buffer, bool skipFsync);
|
|
extern bool mdprefetch(SMgrRelation reln, ForkNumber forknum,
|
|
BlockNumber blocknum);
|
|
extern void mdread(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
|
|
char *buffer);
|
|
extern void mdwrite(SMgrRelation reln, ForkNumber forknum,
|
|
BlockNumber blocknum, char *buffer, bool skipFsync);
|
|
extern void mdwriteback(SMgrRelation reln, ForkNumber forknum,
|
|
BlockNumber blocknum, BlockNumber nblocks);
|
|
extern BlockNumber mdnblocks(SMgrRelation reln, ForkNumber forknum);
|
|
extern void mdtruncate(SMgrRelation reln, ForkNumber forknum,
|
|
BlockNumber old_blocks, BlockNumber nblocks);
|
|
extern void mdimmedsync(SMgrRelation reln, ForkNumber forknum);
|
|
|
|
extern void ForgetDatabaseSyncRequests(Oid dbid);
|
|
extern void DropRelationFiles(RelFileNode *delrels, int ndelrels, bool isRedo);
|
|
|
|
/* md sync callbacks */
|
|
extern int mdsyncfiletag(const FileTag *ftag, char *path);
|
|
extern int mdunlinkfiletag(const FileTag *ftag, char *path);
|
|
extern bool mdfiletagmatches(const FileTag *ftag, const FileTag *candidate);
|
|
|
|
#endif /* MD_H */
|