Postgres Professional
   

Re: High load and iowait but no disk access

From: Tom Lane
Subject: Re: High load and iowait but no disk access
Date: ,
Msg-id: 22550.1125419342@sss.pgh.pa.us
(view: Whole thread, Raw)
In response to: Re: High load and iowait but no disk access  (Rémy Beaumont)
Responses: Re: High load and iowait but no disk access  (Rémy Beaumont)
List: pgsql-performance

Tree view

High load and iowait but no disk access  (Rémy Beaumont, )
 Re: High load and iowait but no disk access  (Rémy Beaumont, )
  Re: High load and iowait but no disk access  (Tom Lane, )
   Re: High load and iowait but no disk access  (Rémy Beaumont, )
 Re: High load and iowait but no disk access  (Michael Stone, )
 Re: High load and iowait but no disk access  (Tom Lane, )
 Re: High load and iowait but no disk access  (Josh Berkus, )
  Re: High load and iowait but no disk access  (Rémy Beaumont, )
 Re: High load and iowait but no disk access  ("Woody Woodring", )
 Re: High load and iowait but no disk access  (Rémy Beaumont, )
 Re: High load and iowait but no disk access  ("Anjan Dave", )
  Re: High load and iowait but no disk access  (, ) 
=?ISO-8859-1?Q?R=E9my_Beaumont?= <> writes:
> On 30-Aug-05, at 12:15, Tom Lane wrote:
>> I know zip about NetApps, but doesn't the 8th column indicate pretty
>> steady disk reads?

> Yes, but they are very low.

Sure, but that's more or less what you'd expect if the thing is randomly
seeking all over the disk :-(.  Just because it's a NetApp doesn't mean
it's got zero seek time.

You did not say what sort of query this is, but I gather that it's doing
an indexscan on a table that is not at all in index order.  Possible
solutions involve reverting to a seqscan (have you forced the planner to
choose an indexscan here, either directly or by lowering random_page_cost?)
or CLUSTERing the table by the index (which would need to be repeated
periodically, so it's not a great answer).

            regards, tom lane

pgsql-performance by date:

Previous:
From: Ralph Mason
Date:
Subject: 'Real' auto vacuum?
Next:
From: mark@mark.mielke.cc
Date:
Subject: Re: 'Real' auto vacuum?