Re: Tracking disk writes? (again) - Mailing list pgsql-general

From Alvaro Herrera
Subject Re: Tracking disk writes? (again)
Date
Msg-id 20070313033027.GT7700@alvh.no-ip.org
Whole thread Raw
In response to Re: Tracking disk writes? (again)  (Tom Lane <tgl@sss.pgh.pa.us>)
Responses Re: Tracking disk writes? (again)
List pgsql-general
Tom Lane wrote:
> Erik Jones <erik@myemma.com> writes:
> > Well, disk reads, cache hits, transactions commited, transactions
> > rolled back, index size and usage, etc. are all able to be tracked vi
> > the pg catalogue tables and views.  But, I haven't seen anything that
> > will give me numbers on actual disk writes done by the database.
>
> One of the reasons you don't see that is that a large fraction of the
> writes are triggered in background by the "bgwriter" process, which
> operates at too low a level to participate in the stats collection
> mechanism.  I'm not sure what would be involved in refactoring things
> sufficiently to make that workable, but it'd be nontrivial.

You mean that bgwriter cannot send stat messages?  Keep in mind that
these are block-level stats, so there's no need to peek at the page
contents ...

--
Alvaro Herrera                                http://www.CommandPrompt.com/
The PostgreSQL Company - Command Prompt, Inc.

pgsql-general by date:

Previous
From: Tom Lane
Date:
Subject: Re: Tracking disk writes? (again)
Next
From: "Tadej Kanizar"
Date:
Subject: Multi DB performance test