On Fri, Jul 12, 2019 at 12:04 PM Luca Ferrari <fluca1978@xxxxxxxxx> wrote: > Since tables are unlogged, I was expecting no much difference in > setting checkpoint_completion_target, but I got (average results): > - checkpoint_completion_target = 0.1 ==> 755 tps > - checkpoint_completation_target = 0.5 ==> 767 tps > - checkpoint_completion_target = 0.9 ==> 681 tps > I've repeated the test with normal (logged) tables, same configuration, and the results are: - checkpoint_completion_target = 0.1 ==> 560 tps - checkpoint_completion_target = 0.5 ==> 624 tps - checkpoint_completion_target = 0.9 ==> 619 tps so here forcing I/O on checkpoints reduces the tps, as I would be expecting. However I'm still unable to get an interpretation of the unlogged table results. That also makes me think it could these tests have no meaning at all. Luca
