From mboxrd@z Thu Jan  1 00:00:00 1970
From: "Nigel Roles" <nigel@9fs.org>
To: "Fans of the OS Plan 9 from Bell Labs" <9fans@cse.psu.edu>
Subject: RE: [9fans] interrupts (non-plan9 related)
Date: Tue, 12 Apr 2005 18:28:57 +0100
Message-ID: <HOEHIDJJJINMLFPOLFJCAECMDGAA.nigel@9fs.org>
MIME-Version: 1.0
Content-Type: text/plain;
	charset="us-ascii"
Content-Transfer-Encoding: 7bit
In-Reply-To: <439d9767ddd20378da8de3abb8972eb9@plan9.ucalgary.ca>
Topicbox-Message-UUID: 368406d4-ead0-11e9-9d60-3106f5b1d025

9fans-bounces+ngr=9fs.org@cse.psu.edu wrote:
> i've got a dual-cpu machine running linux.  i'm looking at sar reports
> for the box and can't really understand what happens -- the machine
> services all interrupts at CPU0 (actually the first hyperthreaded
> part of CPU0). 
> 
> is this supposed to be normal?
> 
> here is how the interrupts were reported just before a major crash:
> 
> 
> 
> 21:30:48 PM CPU i000/s i001/s i002/s i008/s i011/s i014/s i027/s
> i028/s i029/s i030/s 21:30:58 PM 0 99.90 0.00 0.00 0.00 0.00 0.00
> 500.60 1.80 671.90 4.30 21:30:58 PM 1 0.00 0.00 0.00 0.00 0.00 0.00
> 0.00 0.00 0.00 0.00 21:30:58 PM 2 0.00 0.00 0.00 0.00 0.00 0.00 0.00
> 0.00 0.00 0.00 21:30:58 PM 3 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
> 0.00 0.00 21:31:08 PM 0 100.00 0.00 0.00 0.00 0.00 0.00 639.80 0.00
> 2570.20 4.10 21:31:08 PM 1 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
> 0.00 0.00 21:31:08 PM 2 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
> 0.00 21:31:08 PM 3 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
> Average:       0  100.00    0.00    0.00    0.00    0.00    0.00
> 146.48    0.60 2671.07 1318.77
> Average:       1    0.00    0.00    0.00    0.00    0.00    0.00
>   0.00    0.00    0.00    0.00
> Average:       2    0.00    0.00    0.00    0.00    0.00    0.00
>   0.00    0.00    0.00    0.00
> Average:       3    0.00    0.00    0.00    0.00    0.00    0.00
>   0.00    0.00    0.00    0.00

Yes, quite normal.
You have to manually assign interrupts to different processors
if you want to spread the load.