Re: [HACKERS] subscription worker signalling wal writer too much

Поиск

Список

Период

Сортировка

От	Jeff Janes
Тема	Re: [HACKERS] subscription worker signalling wal writer too much
Дата	21 июня 2017 г. 00:31:48
Msg-id	CAMkU=1xBiqfLR+=h+hqKsxnZay4kwhVzu0kCShxsNggdqqdRFg@mail.gmail.com обсуждение исходный текст
Ответ на	Re: [HACKERS] subscription worker signalling wal writer too much (Jeff Janes <jeff.janes@gmail.com>)
Список	pgsql-hackers

Дерево обсуждения

On Thu, Jun 15, 2017 at 3:06 PM, Jeff Janes <jeff.janes@gmail.com> wrote:

This new patch is simpler than the previous one, and more effective at speeding up replication. I assume it would speed up pgbench with synchronous_commit turned off (or against unlogged tables) as well, but I don't think I have the hardware needed to test that.

If I use the 'tpcb-func' script embodied in the attached patch to pgbench, then I can see the performance difference against unlogged tables using 8 clients on a 8 CPU virtual machine. The normal tpcb-like script has too much communication overhead, bouncing from pgbench to the postgres backend 7 times per transaction, to see the difference. I also had to make autovacuum_vacuum_cost_delay=0, otherwise auto analyze holds a snapshot long enough to bloat the HOT chains which injects a great deal of variability into the timings.

Commit 7975c5e0a992ae9 in the 9.6 branch causes a regression of about 10%, and the my patch from the previous email redeems that regression. It also gives the same improvement against 10dev HEAD.

Cheers,

Jeff