1
0
mirror of https://github.com/postgres/postgres.git synced 2025-07-05 07:21:24 +03:00

Marginal cleanup in arrangements for ensuring StrategyHintVacuum is cleared

after an error during VACUUM.  We have a PG_TRY block anyway around the only
call sites, so just reset it in the CATCH clause instead of having
AtEOXact_Buffers blindly do it during xact end.  I think the old code was
actively wrong for the case of a failure during ANALYZE inside a
subtransaction --- the flag wouldn't get cleared until main transaction end.
Probably not worth back-patching though.
This commit is contained in:
Tom Lane
2006-09-17 22:16:22 +00:00
parent f204274191
commit 2e5e856f6b
2 changed files with 4 additions and 7 deletions

View File

@ -13,7 +13,7 @@
*
*
* IDENTIFICATION
* $PostgreSQL: pgsql/src/backend/commands/vacuum.c,v 1.338 2006/08/18 16:09:08 tgl Exp $
* $PostgreSQL: pgsql/src/backend/commands/vacuum.c,v 1.339 2006/09/17 22:16:22 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@ -460,6 +460,8 @@ vacuum(VacuumStmt *vacstmt, List *relids)
{
/* Make sure cost accounting is turned off after error */
VacuumCostActive = false;
/* And reset buffer replacement strategy, too */
StrategyHintVacuum(false);
PG_RE_THROW();
}
PG_END_TRY();
@ -1173,8 +1175,6 @@ vacuum_rel(Oid relid, VacuumStmt *vacstmt, char expected_relkind)
* Now release the session-level lock on the master table.
*/
UnlockRelationIdForSession(&onerelid, lmode);
return;
}