From 33715b1fbba9131744864f23d0310070eaa9c91d Mon Sep 17 00:00:00 2001 From: Antonin Houska Date: Wed, 6 May 2026 09:38:11 +0200 Subject: [PATCH] Distinguish properly when database-specific transaction list should be used. Currently, decoding session that relies on database-specific xl_running_xacts WAL records can also use some information of cluster-wide records and vice versa. Although this approach might reduce the total number of xl_running_xacts records, it's simply not correct. SnapBuildProcessRunningXacts() now decides at the very beginning whether particular record can be used or not. --- src/backend/replication/logical/snapbuild.c | 55 +++++++++++++-------- 1 file changed, 34 insertions(+), 21 deletions(-) diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c index c8309b96ed4..b9661b7d70a 100644 --- a/src/backend/replication/logical/snapbuild.c +++ b/src/backend/replication/logical/snapbuild.c @@ -1157,6 +1157,39 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact ReorderBufferTXN *txn; TransactionId xmin; + /* + * Each decoding session should use either cluster-wide snapshots or + * database-specific ones, but not both. Since the latter can have more + * recent value of oldestRunningXid, builder->xmin could go backwards if + * it was followed by cluster-wide snapshot - see the ->xmin adjustment + * below. + */ + if (!db_specific && OidIsValid(running->dbid)) + return; + + if (db_specific) + { + /* + * Make sure that we have the snapshots needed for startup, as well as + * those for regular cleanup: each time the cluster-wide snapshot is + * created (typically on slot creation or by checkpointer), the + * database-specific snapshot is requested here if the current session + * needs it. + */ + if (!OidIsValid(running->dbid)) + { + LogStandbySnapshot(MyDatabaseId); + + return; + } + /* + * Snapshots issued for other databases do not contain the information + * about transactions in our database. + */ + else if (running->dbid != MyDatabaseId) + return; + } + /* * If we're not consistent yet, inspect the record to see whether it * allows to get closer to being consistent. If we are consistent, dump @@ -1171,17 +1204,7 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact */ if (db_specific) { - /* - * If we must only keep track of transactions running in the - * current database, we need transaction info from exactly that - * database. - */ - if (running->dbid != MyDatabaseId) - { - LogStandbySnapshot(MyDatabaseId); - - return; - } + Assert(running->dbid == MyDatabaseId); /* * We'd better be able to check during scan if the plugin does not @@ -1198,16 +1221,6 @@ SnapBuildProcessRunningXacts(SnapBuild *builder, XLogRecPtr lsn, xl_running_xact else SnapBuildSerialize(builder, lsn); - /* - * Database specific transaction info may exist to reach CONSISTENT state - * faster, however the code below makes no use of it. Moreover, such - * record might cause problems because the following normal (cluster-wide) - * record can have lower value of oldestRunningXid. In that case, let's - * wait with the cleanup for the next regular cluster-wide record. - */ - if (OidIsValid(running->dbid)) - return; - /* * Update range of interesting xids based on the running xacts * information. We don't increase ->xmax using it, because once we are in -- 2.47.3