From 08302a39743c085a4be1d218e61abf225ab13bab Mon Sep 17 00:00:00 2001 From: Heikki Linnakangas Date: Wed, 27 Nov 2013 13:10:16 +0200 Subject: [PATCH] Don't update relfrozenxid if any pages were skipped. Vacuum recognizes that it can update relfrozenxid by checking whether it has processed all pages of a relation. Unfortunately it performed that check after truncating the dead pages at the end of the relation, and used the new number of pages to decide whether all pages have been scanned. If the new number of pages happened to be smaller or equal to the number of pages scanned, it incorrectly decided that all pages were scanned. This can lead to relfrozenxid being updated, even though some pages were skipped that still contain old XIDs. That can lead to data loss due to xid wraparounds with some rows suddenly missing. This likely has escaped notice so far because it takes a large number (~2^31) of xids being used to see the effect, while a full-table vacuum before that would fix the issue. The incorrect logic was introduced by commit b4b6923e03f4d29636a94f6f4cc2f5cf6298b8c8. Backpatch this fix down to 8.4, like that commit. Andres Freund, with some modifications by me. --- src/backend/commands/vacuumlazy.c | 31 +++++++++++++++++++++---------- 1 file changed, 21 insertions(+), 10 deletions(-) diff --git a/src/backend/commands/vacuumlazy.c b/src/backend/commands/vacuumlazy.c index 11d0192931..93ea085124 100644 --- a/src/backend/commands/vacuumlazy.c +++ b/src/backend/commands/vacuumlazy.c @@ -178,7 +178,8 @@ lazy_vacuum_rel(Relation onerel, VacuumStmt *vacstmt, int usecs; double read_rate, write_rate; - bool scan_all; + bool scan_all; /* should we scan all pages? */ + bool scanned_all; /* did we actually scan all pages? */ TransactionId freezeTableLimit; BlockNumber new_rel_pages; double new_rel_tuples; @@ -225,6 +226,21 @@ lazy_vacuum_rel(Relation onerel, VacuumStmt *vacstmt, /* Done with indexes */ vac_close_indexes(nindexes, Irel, NoLock); + /* + * Compute whether we actually scanned the whole relation. If we did, we + * can adjust relfrozenxid and relminmxid. + * + * NB: We need to check this before truncating the relation, because that + * will change ->rel_pages. + */ + if (vacrelstats->scanned_pages < vacrelstats->rel_pages) + { + Assert(!scan_all); + scanned_all = false; + } + else + scanned_all = true; + /* * Optionally truncate the relation. * @@ -254,8 +270,8 @@ lazy_vacuum_rel(Relation onerel, VacuumStmt *vacstmt, * is all-visible we'd definitely like to know that. But clamp the value * to be not more than what we're setting relpages to. * - * Also, don't change relfrozenxid if we skipped any pages, since then we - * don't know for certain that all tuples have a newer xmin. + * Also, don't change relfrozenxid/relminmxid if we skipped any pages, + * since then we don't know for certain that all tuples have a newer xmin. */ new_rel_pages = vacrelstats->rel_pages; new_rel_tuples = vacrelstats->new_rel_tuples; @@ -269,13 +285,8 @@ lazy_vacuum_rel(Relation onerel, VacuumStmt *vacstmt, if (new_rel_allvisible > new_rel_pages) new_rel_allvisible = new_rel_pages; - new_frozen_xid = FreezeLimit; - if (vacrelstats->scanned_pages < vacrelstats->rel_pages) - new_frozen_xid = InvalidTransactionId; - - new_min_multi = MultiXactCutoff; - if (vacrelstats->scanned_pages < vacrelstats->rel_pages) - new_min_multi = InvalidMultiXactId; + new_frozen_xid = scanned_all ? FreezeLimit : InvalidTransactionId; + new_min_multi = scanned_all ? MultiXactCutoff : InvalidMultiXactId; vac_update_relstats(onerel, new_rel_pages, -- 2.40.0