database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-11-03 09:13:20 +03:00
Code Activity

Fix old-fd issues using global barriers everywhere.

Browse Source 
Commits 4eb21763 and b74e94dc introduced a way to force every backend to
close all relation files, to fix an ancient Windows-only bug.

This commit extends that behavior to all operating systems and adds
a couple of extra barrier points, to fix a totally different class of
bug: the reuse of relfilenodes in scenarios that have no other kind of
cache invalidation to prevent file descriptor mix-ups.

In all releases, data corruption could occur when you moved a database
to another tablespace and then back again.  Despite that, no back-patch
for now as the infrastructure required is too new and invasive.  In
master only, since commit aa010514, it could also happen when using
CREATE DATABASE with a user-supplied OID or via pg_upgrade.

Author: Andres Freund <andres@anarazel.de>
Reviewed-by: Robert Haas <robertmhaas@gmail.com>
Reviewed-by: Thomas Munro <thomas.munro@gmail.com>
Discussion: https://postgr.es/m/20220209220004.kb3dgtn2x2k2gtdm%40alap3.anarazel.de
This commit is contained in:
Thomas Munro
2022-05-07 15:19:52 +12:00
parent b74e94dc27
commit e2f65f4255
5 changed files with 241 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/backend/commands/dbcommands.c
View File

@@ -1687,10 +1687,8 @@ dropdb(const char *dbname, bool missing_ok, bool force)
*/
RequestCheckpoint(CHECKPOINT_IMMEDIATE | CHECKPOINT_FORCE | CHECKPOINT_WAIT);
#if defined(USE_BARRIER_SMGRRELEASE)
/* Close all smgr fds in all backends. */
WaitForProcSignalBarrier(EmitProcSignalBarrier(PROCSIGNAL_BARRIER_SMGRRELEASE));
#endif
/*
* Remove all tablespace subdirs belonging to the database.
@@ -1940,10 +1938,8 @@ movedb(const char *dbname, const char *tblspcname)
RequestCheckpoint(CHECKPOINT_IMMEDIATE | CHECKPOINT_FORCE | CHECKPOINT_WAIT
| CHECKPOINT_FLUSH_ALL);
#if defined(USE_BARRIER_SMGRRELEASE)
/* Close all smgr fds in all backends. */
WaitForProcSignalBarrier(EmitProcSignalBarrier(PROCSIGNAL_BARRIER_SMGRRELEASE));
#endif
/*
* Now drop all buffers holding data of the target database; they should
@@ -3054,6 +3050,9 @@ dbase_redo(XLogReaderState *record)
*/
FlushDatabaseBuffers(xlrec->src_db_id);
/* Close all sgmr fds in all backends. */
WaitForProcSignalBarrier(EmitProcSignalBarrier(PROCSIGNAL_BARRIER_SMGRRELEASE));
/*
* Copy this subdirectory to the new location
*
@@ -3111,10 +3110,8 @@ dbase_redo(XLogReaderState *record)
/* Clean out the xlog relcache too */
XLogDropDatabase(xlrec->db_id);
#if defined(USE_BARRIER_SMGRRELEASE)
/* Close all sgmr fds in all backends. */
WaitForProcSignalBarrier(EmitProcSignalBarrier(PROCSIGNAL_BARRIER_SMGRRELEASE));
#endif
for (i = 0; i < xlrec->ntablespaces; i++)
{

11
src/backend/commands/tablespace.c
View File

@@ -548,11 +548,10 @@ DropTableSpace(DropTableSpaceStmt *stmt)
* use a global barrier to ask all backends to close all files, and
* wait until they're finished.
*/
#if defined(USE_BARRIER_SMGRRELEASE)
LWLockRelease(TablespaceCreateLock);
WaitForProcSignalBarrier(EmitProcSignalBarrier(PROCSIGNAL_BARRIER_SMGRRELEASE));
LWLockAcquire(TablespaceCreateLock, LW_EXCLUSIVE);
#endif
/* And now try again. */
if (!destroy_tablespace_directories(tablespaceoid, false))
{
@@ -1574,6 +1573,9 @@ tblspc_redo(XLogReaderState *record)
{
xl_tblspc_drop_rec *xlrec = (xl_tblspc_drop_rec *) XLogRecGetData(record);
/* Close all smgr fds in all backends. */
WaitForProcSignalBarrier(EmitProcSignalBarrier(PROCSIGNAL_BARRIER_SMGRRELEASE));
/*
* If we issued a WAL record for a drop tablespace it implies that
* there were no files in it at all when the DROP was done. That means
@@ -1591,11 +1593,6 @@ tblspc_redo(XLogReaderState *record)
*/
if (!destroy_tablespace_directories(xlrec->ts_id, true))
{
#if defined(USE_BARRIER_SMGRRELEASE)
/* Close all smgr fds in all backends. */
WaitForProcSignalBarrier(EmitProcSignalBarrier(PROCSIGNAL_BARRIER_SMGRRELEASE));
#endif
ResolveRecoveryConflictWithTablespace(xlrec->ts_id);
/*