Fix remote position tracking in logical replication

petere · petere · commit fe7bbc4ddb82 · 2017-04-04T08:24:32.000-04:00
We need to set the origin remote position to end_lsn, not commit_lsn, as
commit_lsn is the start of commit record, and we use the origin remote
position as start position when restarting replication stream.  If we'd
use commit_lsn, we could request data that we already received from the
remote server after a crash of a downstream server.

Author: Petr Jelinek &lt;petr.jelinek@2ndquadrant.com&gt;
diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c
@@ -421,9 +421,6 @@ apply_handle_begin(StringInfo s)
 
 	logicalrep_read_begin(s, &begin_data);
 
-	replorigin_session_origin_timestamp = begin_data.committime;
-	replorigin_session_origin_lsn = begin_data.final_lsn;
-
 	remote_final_lsn = begin_data.final_lsn;
 
 	in_remote_transaction = true;
@@ -443,14 +440,18 @@ apply_handle_commit(StringInfo s)
 
 	logicalrep_read_commit(s, &commit_data);
 
-	Assert(commit_data.commit_lsn == replorigin_session_origin_lsn);
-	Assert(commit_data.committime == replorigin_session_origin_timestamp);
-
 	Assert(commit_data.commit_lsn == remote_final_lsn);
 
 	/* The synchronization worker runs in single transaction. */
 	if (IsTransactionState() && !am_tablesync_worker())
 	{
+		/*
+		 * Update origin state so we can restart streaming from correct
+		 * position in case of crash.
+		 */
+		replorigin_session_origin_lsn = commit_data.end_lsn;
+		replorigin_session_origin_timestamp = commit_data.committime;
+
 		CommitTransactionCommand();
 
 		store_flush_position(commit_data.end_lsn);
