From 70dc0fe41f0aa6afb15358b6362900259e3d08a3 Mon Sep 17 00:00:00 2001 From: Heikki Linnakangas Date: Thu, 19 Mar 2026 21:27:51 +0200 Subject: [PATCH 1/1] Fix multixact backwards-compatibility with CHECKPOINT race condition If a CHECKPOINT record with nextMulti N is written to the WAL before the CREATE_ID record for N, and N happens to be the first multixid on an offset page, the backwards compatibility logic to tolerate WAL generated by older minor versions failed to compensate for the missing XLOG_MULTIXACT_ZERO_OFF_PAGE record. In that case, the latest_page_number was initialized at the start of WAL replay to the page for nextMulti from the CHECKPOINT record, even if we had not seen the CREATE_ID record for that multixid yet, which fooled the backwards compatibility logic to think that the page was already initialized. To fix, track the last XLOG_MULTIXACT_ZERO_OFF_PAGE that we've seen separately from latest_page_number. If we haven't seen any XLOG_MULTIXACT_ZERO_OFF_PAGE records yet, use SimpleLruDoesPhysicalPageExist() to check if the page needs to be initialized. --- src/backend/access/transam/multixact.c | 65 +++++++++++++++++++------- 1 file changed, 47 insertions(+), 18 deletions(-) diff --git a/src/backend/access/transam/multixact.c b/src/backend/access/transam/multixact.c index f9bd1dd19e6..5dcb7f9068f 100644 --- a/src/backend/access/transam/multixact.c +++ b/src/backend/access/transam/multixact.c @@ -417,7 +417,17 @@ static MemoryContext MXactContext = NULL; #define debug_elog6(a,b,c,d,e,f) #endif -/* hack to deal with WAL generated with older minor versions */ +/* + * Hack to deal with WAL generated with older minor versions. + * + * last_initialized_offsets_page is the XLOG_MULTIXACT_ZERO_OFF_PAGE record + * that we saw during WAL replay, or -1 if we haven't seen any yet. + * + * pre_initialized_offsets_page is the last page that was implicitly + * initialized by replaying a XLOG_MULTIXACT_CREATE_ID record, when we had not + * seen a XLOG_MULTIXACT_ZERO_OFF_PAGE record for the page yet. + */ +static int64 last_initialized_offsets_page = -1; static int64 pre_initialized_offsets_page = -1; /* internal MultiXactId management */ @@ -982,29 +992,46 @@ RecordNewMultiXact(MultiXactId multi, MultiXactOffset offset, * such a version, the next page might not be initialized yet. Initialize * it now. */ - if (InRecovery && - next_pageno != pageno && - pg_atomic_read_u64(&MultiXactOffsetCtl->shared->latest_page_number) == pageno) + if (InRecovery && next_pageno != pageno) { - elog(DEBUG1, "next offsets page is not initialized, initializing it now"); + bool init_needed; - lock = SimpleLruGetBankLock(MultiXactOffsetCtl, next_pageno); - LWLockAcquire(lock, LW_EXCLUSIVE); + /* + * Check if the page exists. SimpleLruDoesPhysicalPageExist() is + * somewhat expensive, however, so if we have seen any + * XLOG_MULTIXACT_ZERO_OFF_PAGE records during replay, we trust + * without checking that the last page initialized by + * XLOG_MULTIXACT_ZERO_OFF_PAGE already exists, and the one after that + * does not. + */ + if (last_initialized_offsets_page == -1) + init_needed = !SimpleLruDoesPhysicalPageExist(MultiXactOffsetCtl, next_pageno); + else + init_needed = (last_initialized_offsets_page == pageno); - /* Create and zero the page */ - slotno = SimpleLruZeroPage(MultiXactOffsetCtl, next_pageno); + if (init_needed) + { + elog(DEBUG1, "next offsets page is not initialized, initializing it now"); - /* Make sure it's written out */ - SimpleLruWritePage(MultiXactOffsetCtl, slotno); - Assert(!MultiXactOffsetCtl->shared->page_dirty[slotno]); + lock = SimpleLruGetBankLock(MultiXactOffsetCtl, next_pageno); + LWLockAcquire(lock, LW_EXCLUSIVE); - LWLockRelease(lock); + /* Create and zero the page */ + slotno = SimpleLruZeroPage(MultiXactOffsetCtl, next_pageno); - /* - * Remember that we initialized the page, so that we don't zero it - * again at the XLOG_MULTIXACT_ZERO_OFF_PAGE record. - */ - pre_initialized_offsets_page = next_pageno; + /* Make sure it's written out */ + SimpleLruWritePage(MultiXactOffsetCtl, slotno); + Assert(!MultiXactOffsetCtl->shared->page_dirty[slotno]); + + LWLockRelease(lock); + + /* + * Remember that we initialized the page, so that we don't zero it + * again at the XLOG_MULTIXACT_ZERO_OFF_PAGE record. + */ + pre_initialized_offsets_page = next_pageno; + last_initialized_offsets_page = next_pageno; + } } /* @@ -3560,6 +3587,8 @@ multixact_redo(XLogReaderState *record) Assert(!MultiXactOffsetCtl->shared->page_dirty[slotno]); LWLockRelease(lock); + + last_initialized_offsets_page = pageno; } else elog(DEBUG1, "skipping initialization of offsets page " INT64_FORMAT " because it was already initialized on multixid creation", pageno); -- 2.47.3