From 7db0dc0eac4512253c2ec0e6bea60ecd2d7bea27 Mon Sep 17 00:00:00 2001 From: Noah Misch Date: Sun, 6 Oct 2013 09:56:43 -0400 Subject: [PATCH] pgbench: Comment on thread timing hazards. Reviewed by Fabien COELHO. --- contrib/pgbench/pgbench.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/contrib/pgbench/pgbench.c b/contrib/pgbench/pgbench.c index 926246e67b..816400f6dd 100644 --- a/contrib/pgbench/pgbench.c +++ b/contrib/pgbench/pgbench.c @@ -2896,7 +2896,16 @@ main(int argc, char **argv) } disconnect_all(state, nclients); - /* get end time */ + /* + * XXX We compute results as though every client of every thread started + * and finished at the same time. That model can diverge noticeably from + * reality for a short benchmark run involving relatively many threads. + * The first thread may process notably many transactions before the last + * thread begins. Improving the model alone would bring limited benefit, + * because performance during those periods of partial thread count can + * easily exceed steady state performance. This is one of the many ways + * short runs convey deceptive performance figures. + */ INSTR_TIME_SET_CURRENT(total_time); INSTR_TIME_SUBTRACT(total_time, start_time); printResults(ttype, total_xacts, nclients, threads, nthreads, -- 2.40.0