On Sat, Aug 27, 2011 at 03:57:16PM +0200, Tomas Vondra wrote: > On 27 Srpen 2011, 6:01, Noah Misch wrote: > > On Fri, Aug 26, 2011 at 10:46:33AM +0200, Tomas Vondra wrote: > >> 1. collect pg_stat_bgwriter stats > >> 2. run pgbench for 10 minutes > >> 3. collect pg_stat_bgwriter stats (to compute difference with (1)) > >> 4. kill the postmaster > >> > >> The problem is that when checkpoint stats are collected, there might be > >> a > >> checkpoint in progress and in that case the stats are incomplete. In > >> some > >> cases (especially with very small db blocks) this has significant impact > >> because the checkpoints are less frequent. > > > > Could you remove this hazard by adding a step "2a. psql -c CHECKPOINT"? > > I already do that, but it really does not solve the issue. It just aligns > the first expected 'timed' checkpoint, it does not solve the problem with > in-progress checkpoints unless the runs behave exactly the same (and > that's the boring case).
To clarify, run that command _after_ the 10-minute pgbench run. It blocks until completion of both the in-progress checkpoint, if any, and the requested checkpoint. -- Noah Misch http://www.2ndQuadrant.com/ PostgreSQL Development, 24x7 Support, Training & Services -- Sent via pgsql-hackers mailing list (email@example.com) To make changes to your subscription: http://www.postgresql.org/mailpref/pgsql-hackers