From: "Sindre Solem" <sindre.solem@emmaedb.no>
Newsgroups: comp.databases.oracle.server
References: <y12Z5.1073$pj.33475@news1.oke.nextra.no> <912kjm$6o4$1@nnrp1.deja.com> <912m69$81a$1@nnrp1.deja.com> <C_5Z5.1316$pj.37861@news1.oke.nextra.no> <912vgu$g1a$1@nnrp1.deja.com>
Subject: Re: Hardware tips
Lines: 30
X-Priority: 3
X-MSMail-Priority: Normal
X-Newsreader: Microsoft Outlook Express 5.50.4133.2400
X-MimeOLE: Produced By Microsoft MimeOLE V5.50.4133.2400
Message-ID: <GGmZ5.2040$pj.60898@news1.oke.nextra.no>
Date: Tue, 12 Dec 2000 11:00:06 +0100
NNTP-Posting-Host: 62.92.100.96
X-Complaints-To: news-abuse@nextra.no
X-Trace: news1.oke.nextra.no 976615206 62.92.100.96 (Tue, 12 Dec 2000 11:00:06 MET)
NNTP-Posting-Date: Tue, 12 Dec 2000 11:00:06 MET
Organization: Nextra Public Access



<denevge@my-deja.com> skrev i melding news:912vgu$g1a$1@nnrp1.deja.com...
> execute the following : sar -u <interval> <number of samples>
> eg sar -u 2 5 : this will give you 5 metrics.
> Here you can see how the system is performing :
>   how many % of the cpu is given to user processes
>   how many % of the cpu is given to system processes
>   how many % of the cpu is waiting for i/o
>   how manu % of the cpu is idle

Running this a few times I get values from 0 to 96 for waiting for i/o.
Should it really get that high?

> if you see a large "waiting for i/o" this means there could be a
> bottleneck on the i/o performance.
> If so, execute sar -q x y.  Look at the run-queue.  If it's +5, you
> have a cpu performance problem. ( could be cause by a high "waiting for
> i/o )
> If "waiting for i/o" is high, check vmstat to see if you paging.

vmstat gives these paging statistics:
        page
re  mf pi po fr de sr
 0  21 26  0  0  0  0

This means that nothing has been paged out, right?