From 0f404c5812471d21c1d006b4e5f354ca216cea22 Mon Sep 17 00:00:00 2001 From: Daniel Gustafsson Date: Wed, 30 Apr 2025 20:36:24 +0200 Subject: [PATCH] Fix assertion failure in snapshot building Clear any potential stale next_phase_at value from the snapshot builder which otherwise may trip an assertion check ensuring that there is no next_phase_at value. This can be reproduced by running 80 concurrent sessions like the below where $c is a loop counter (assumes there has been 1..$c databases created) : echo " CREATE TABLE replication_example(id SERIAL PRIMARY KEY, somedata int, text varchar(120)); SELECT 'init' FROM pg_create_logical_replication_slot('regression_slot_$c', 'test_decoding'); SELECT data FROM pg_logical_slot_get_changes('regression_slot_$c', NULL, NULL, 'include-xids', '0', 'skip-empty-xacts', '1'); " | psql -d regress_$c >>psql.log & This was originally committed as 48efb23 and backpatched down to v16, but since then there have been reports of this happening on v14 and v15 as well so this is a backpatch of 48efb23 down to 14. Bug: #17695 Author: Masahiko Sawada Reviewed-by: Alexander Lakhin Reported-by: bowenshi Reported-by: Alexander Pyhalov Reported-by: Teja Mupparti Discussion: https://postgr.es/m/17695-6be9277c9295985f@postgresql.org Backpatch-through: v14 --- src/backend/replication/logical/snapbuild.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index 0b303f9a235..2ca8e6e9aff 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -2028,8 +2028,12 @@ SnapBuildRestore(SnapBuild *builder, XLogRecPtr lsn) if (TransactionIdPrecedes(ondisk.builder.xmin, builder->initial_xmin_horizon)) goto snapshot_not_interesting; - /* consistent snapshots have no next phase */ + /* + * Consistent snapshots have no next phase. Reset next_phase_at as it is + * possible that an old value may remain. + */ Assert(ondisk.builder.next_phase_at == InvalidTransactionId); + builder->next_phase_at = InvalidTransactionId; /* ok, we think the snapshot is sensible, copy over everything important */ builder->xmin = ondisk.builder.xmin;