| From: | Alvaro Herrera <alvherre(at)commandprompt(dot)com> | 
|---|---|
| To: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> | 
| Cc: | Erik Jones <erik(at)myemma(dot)com>, Ron Johnson <ron(dot)l(dot)johnson(at)cox(dot)net>, pgsql-general(at)postgresql(dot)org | 
| Subject: | Re: Tracking disk writes? (again) | 
| Date: | 2007-03-13 03:30:27 | 
| Message-ID: | 20070313033027.GT7700@alvh.no-ip.org | 
| Views: | Whole Thread | Raw Message | Download mbox | Resend email | 
| Thread: | |
| Lists: | pgsql-general | 
Tom Lane wrote:
> Erik Jones <erik(at)myemma(dot)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.
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Timasmith | 2007-03-13 03:39:10 | Re: which is more scalable for the database? | 
| Previous Message | Tom Lane | 2007-03-13 01:35:19 | Re: Tracking disk writes? (again) |