Re: Huge iowait during checkpoint finish - Mailing list pgsql-general

From Craig Ringer
Subject Re: Huge iowait during checkpoint finish
Date
Msg-id 4B4BCECF.5080508@postnewspapers.com.au
Whole thread Raw
In response to Re: Huge iowait during checkpoint finish  (Greg Smith <greg@2ndquadrant.com>)
List pgsql-general
Greg Smith wrote:

> If the old system had a write caching card, and the new one doesn't
> that's certainly your most likely suspect for the source of the
> slowdown.

Note that it's even possible that the old system had a card with write
caching enabled, but *no* battery backed cache. That's crazily
dangerous, but does get you the speed benefits of write caching without
the need for a BBU. I only mention this to help explain a possible
performance difference - you should NEVER do this if you care about your
data.

--
Craig Ringer

pgsql-general by date:

Previous
From: Omar Mehmood
Date:
Subject: Re: replication from multiple "master" servers to a single read-only slave
Next
From: Craig Ringer
Date:
Subject: Re: replication from multiple "master" servers to a single read-only slave