Re: pg_basebackup - odd performance

Поиск
Список
Период
Сортировка
От Mike Blackwell
Тема Re: pg_basebackup - odd performance
Дата
Msg-id CANPAkgvxjyxsXAmN53D6cn_cWm1L_3Ex-NG4uL20dPp3v62EAQ@mail.gmail.com
обсуждение исходный текст
Ответ на Re: pg_basebackup - odd performance  (Jov <amutu@amutu.com>)
Список pgsql-performance
Thanks for your reply.  Adding '-c fast' does seem to improve the initial delay.  I'm still seeing delays of several minutes between write bursts.  The server has light OLTP loading.

__________________________________________________________________________________
Mike Blackwell | Technical Analyst, Distribution Services/Rollout Management | RR Donnelley
1750 Wallace Ave | St Charles, IL 60174-3401
Office: 630.313.7818
Mike.Blackwell@rrd.com
http://www.rrdonnelley.com



On Mon, Oct 6, 2014 at 9:59 PM, Jov <amutu@amutu.com> wrote:

what is the cmd?the default checkpoint method is spread,so pg_basebackup will wait the checkpoint complete on the master.you can set the checkpoint method to fast to avoid the waiting.

2014年10月7日 2:54 AM于 "Mike Blackwell" <mike.blackwell@rrd.com>写道:

I'm seeing some strange behavior running pg_basebackup on 9.3.5.  It appears that there are long pauses - up to a couple of minutes - between relatively short bursts of disk activity.  

I'm not noticing any lock requests outstanding.  What might I be missing?

__________________________________________________________________________________
Mike Blackwell | Technical Analyst, Distribution Services/Rollout Management | RR Donnelley
1750 Wallace Ave | St Charles, IL 60174-3401
Office: 630.313.7818
Mike.Blackwell@rrd.com
http://www.rrdonnelley.com



В списке pgsql-performance по дате отправления:

Предыдущее
От: Andrey Lizenko
Дата:
Сообщение: query plan question, nested loop vs hash join
Следующее
От: Marti Raudsepp
Дата:
Сообщение: Re: query plan question, nested loop vs hash join