diff options
| author | Tom Lane <tgl@sss.pgh.pa.us> | 2021-04-20 16:58:30 -0400 |
|---|---|---|
| committer | Tom Lane <tgl@sss.pgh.pa.us> | 2021-04-20 17:01:49 -0400 |
| commit | 9e41148229192dccc4bcc40f53af588b73d8ffea (patch) | |
| tree | 3314c5c3920022d3ad4b76c66cd721a076774d87 /src/backend/access/transam/xlogprefetch.c | |
| parent | db01f797dd48f826c62e1b8eea70f11fe7ff3efc (diff) | |
| download | postgresql-9e41148229192dccc4bcc40f53af588b73d8ffea.tar.gz postgresql-9e41148229192dccc4bcc40f53af588b73d8ffea.zip | |
Fix under-parenthesized XLogRecHasBlockRef() macro.
Commit f003d9f87 left this macro with inadequate (or, one could say,
too much) parenthesization. Which was catastrophic to the correctness
of calls such as "if (!XLogRecHasBlockRef(record, 1)) ...". There
are only a few of those, which perhaps explains why we didn't notice
immediately (with our general weakness of WAL replay testing being
another factor). I found it by debugging intermittent replay failures
like
2021-04-08 14:33:30.191 EDT [29463] PANIC: failed to locate backup block with ID 1
2021-04-08 14:33:30.191 EDT [29463] CONTEXT: WAL redo at 0/95D3438 for SPGist/ADD_NODE: off 1; blkref #0: rel 1663/16384/25998, blk 1
Diffstat (limited to 'src/backend/access/transam/xlogprefetch.c')
0 files changed, 0 insertions, 0 deletions