diff options
| author | Tom Lane <tgl@sss.pgh.pa.us> | 2006-09-17 22:16:22 +0000 |
|---|---|---|
| committer | Tom Lane <tgl@sss.pgh.pa.us> | 2006-09-17 22:16:22 +0000 |
| commit | 2e5e856f6b4f4e7445ec4b14fc4504469f6f4f54 (patch) | |
| tree | a5787778a831c23ad54beb0348e635b393eea944 /src/backend/access/gist/gistxlog.c | |
| parent | f204274191f742deb489f53ebead03a0ed0a48eb (diff) | |
| download | postgresql-2e5e856f6b4f4e7445ec4b14fc4504469f6f4f54.tar.gz postgresql-2e5e856f6b4f4e7445ec4b14fc4504469f6f4f54.zip | |
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.
Diffstat (limited to 'src/backend/access/gist/gistxlog.c')
0 files changed, 0 insertions, 0 deletions