From e2f65f42555ff531c6d7c8f151526b4ef7c016f8 Mon Sep 17 00:00:00 2001 From: Thomas Munro Date: Sat, 7 May 2022 15:19:52 +1200 Subject: Fix old-fd issues using global barriers everywhere. 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 Reviewed-by: Robert Haas Reviewed-by: Thomas Munro Discussion: https://postgr.es/m/20220209220004.kb3dgtn2x2k2gtdm%40alap3.anarazel.de --- src/backend/commands/tablespace.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'src/backend/commands/tablespace.c') diff --git a/src/backend/commands/tablespace.c b/src/backend/commands/tablespace.c index 40514ab550f..822d65287ef 100644 --- a/src/backend/commands/tablespace.c +++ b/src/backend/commands/tablespace.c @@ -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); /* -- cgit v1.2.3