Re: PostgreSQL Reliability when fsync = false on

From: Hannu Krosing <hannu(at)tm(dot)ee>
To: Rod Taylor <rbt(at)rbt(dot)ca>
Cc: Federico Sevilla III <jijo(at)free(dot)net(dot)ph>, PostgreSQL Performance Mailing List <pgsql-performance(at)postgresql(dot)org>, Linux-XFS Mailing List <linux-xfs(at)oss(dot)sgi(dot)com>
Subject: Re: PostgreSQL Reliability when fsync = false on
Date: 2003-09-04 06:55:27
Message-ID: 1062658526.6270.5.camel@fuji.krosing.net
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-performance

Rod Taylor kirjutas N, 04.09.2003 kell 06:36:
> Another alternative is
> to buy a small 15krpm disk dedicated for WAL. In theory you can achieve
> one commit per rotation.

One commit per rotation would still be only 15000/60. = 250 tps, but
fortunately you can get better results if you use multiple concurrent
backends, then in the best case you can get one commit per backend per
rotation.

-----------------
Hannu

In response to

Browse pgsql-performance by date

  From Date Subject
Next Message Shridhar Daithankar 2003-09-04 07:04:51 Re: PostgreSQL Reliability when fsync = false on Linux-XFS
Previous Message Tom Lane 2003-09-04 05:03:08 Re: SELECT's take a long time compared to other DBMS