On Fri, Feb 28, 2025 at 02:41:34PM +0900, Michael Paquier wrote: > With smaller records, the loop can become hotter, can't it? Also, > there can be a high number of WAL senders on a single node, and I've > heard of some customers with complex logical decoding deployments with > dozens of logical WAL senders. Isn't there a risk of having this code > path become a point of contention? It seems to me that we should > benchmark this change more carefully, perhaps even reduce the > frequency of the report calls.
One idea here would be to have on a single host one server with a set of N pg_receivewal processes dumping their WAL segments into a tmpfs, while a single session generates a bunch of records with a minimal size using pg_logical_emit_message(). Monitoring the maximum replication lag with pg_stat_replication and looking at some perf profiles of the cluster should show how these stats reports affect the replication setup efficiency. -- Michael
signature.asc
Description: PGP signature
