From: | Noah Misch <noah(at)leadboat(dot)com> |
---|---|
To: | pgsql-committers(at)lists(dot)postgresql(dot)org |
Subject: | pgsql: Fix inplace update buffer self-deadlock. |
Date: | 2024-11-02 16:08:47 |
Message-ID: | [email protected] |
Views: | Whole Thread | Raw Message | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-committers |
Fix inplace update buffer self-deadlock.
A CacheInvalidateHeapTuple* callee might call
CatalogCacheInitializeCache(), which needs a relcache entry. Acquiring
a valid relcache entry might scan pg_class. Hence, to prevent
undetected LWLock self-deadlock, CacheInvalidateHeapTuple* callers must
not hold BUFFER_LOCK_EXCLUSIVE on buffers of pg_class. Move the
CacheInvalidateHeapTupleInplace() before the BUFFER_LOCK_EXCLUSIVE. No
back-patch, since I've reverted commit
243e9b40f1b2dd09d6e5bf91ebf6e822a2cd3704 from non-master branches.
Reported by Alexander Lakhin. Reviewed by Alexander Lakhin.
Discussion: https://postgr.es/m/[email protected]
Branch
------
master
Modified Files
--------------
src/backend/access/heap/heapam.c | 21 +++++++++++++--------
src/backend/utils/cache/inval.c | 12 ++++++++++++
src/include/utils/inval.h | 1 +
3 files changed, 26 insertions(+), 8 deletions(-)
From | Date | Subject | |
---|---|---|---|
Next Message | Tom Lane | 2024-11-03 02:32:56 | Re: pgsql: Move I/O before the index_update_stats() buffer lock region. |
Previous Message | Bruce Momjian | 2024-11-01 20:38:44 | pgsql: doc: clarify text around MVCC example query |