From: Rémy Beaumont <remyb@medrium.com>
To: Tom Lane <tgl@sss.pgh.pa.us>
Cc: pgsql-performance@postgresql.org
Subject: Re: High load and iowait but no disk access
Date: Tue, 30 Aug 2005 12:19:30 -0400
Message-ID: <2fa5224f3e5af53598e33d115a2af980@medrium.com> (raw)
In-Reply-To: <22417.1125418551@sss.pgh.pa.us>
References: <bcd92b00545ffeef542f68666144099d@medrium.com>
<22417.1125418551@sss.pgh.pa.us>
On 30-Aug-05, at 12:15, Tom Lane wrote:
> =?ISO-8859-1?Q?R=E9my_Beaumont?= <remyb@medrium.com> writes:
>> The stats of the NetApp do confirm that it is sitting idle.
>
> Really?
>
>> CPU NFS CIFS HTTP Total Net kB/s Disk kB/s Tape kB/s
>> Cache Cache CP CP Disk DAFS FCP iSCSI FCP kB/s
>> in out read write read write
>> age hit time ty util in out
>> 2% 0 0 0 139 0 0 2788 0 0 0
>> 3 96% 0% - 15% 0 139 0 3 2277
>> 2% 0 0 0 144 0 0 2504 0 0 0
>> 3 96% 0% - 18% 0 144 0 3 2150
>> 2% 0 0 0 130 0 0 2212 0 0 0
>> 3 96% 0% - 13% 0 130 0 3 1879
>> 3% 0 0 0 169 0 0 2937 80 0 0
>> 3 96% 0% - 13% 0 169 0 4 2718
>> 2% 0 0 0 139 0 0 2448 0 0 0
>> 3 96% 0% - 12% 0 139 0 3 2096
>
> I know zip about NetApps, but doesn't the 8th column indicate pretty
> steady disk reads?
Yes, but they are very low.
At 15% usage, it's pretty much sitting idle if you consider that the OS
reports that one of the processor is spending more then 80% of it's
time in IOwait.
Rémy
>
> regards, tom lane
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: pgsql-performance@postgresql.org
Cc: remyb@medrium.com, tgl@sss.pgh.pa.us
Subject: Re: High load and iowait but no disk access
In-Reply-To: <2fa5224f3e5af53598e33d115a2af980@medrium.com>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox