Subject: top CPU enumeration [was: Re: NetBSD 2.0 test drive at HP site]
To: Ben Collver <collver@peak.org>
From: Hubert Feyrer <hubert@feyrer.de>
List: netbsd-advocacy
Date: 02/05/2005 15:20:25
On Sat, 5 Feb 2005, Ben Collver wrote:
>> $ top
>> load averages: 0.46, 0.21, 0.12 07:55:02
>> 30 processes: 28 sleeping, 2 on processor
>> CPU0 states: 0.0% user, 0.0% nice, 0.0% system, 0.0% interrupt, 100% idle
>> CPU1 states: 100% user, 0.0% nice, 0.0% system, 0.0% interrupt, 0.0% idle
>> Memory: 19M Act, 548K Wired, 2552K Exec, 14M File, 1957M Free
>> Swap: 2048M Total, 2048M Free
>>
>> PID USERNAME PRI NICE SIZE RES STATE TIME WCPU CPU COMMAND
>> 1819 hubertf 53 0 128K 580K CPU/0 0:21 97.50% 65.09% sh
>> 1804 hubertf 18 0 220K 756K pause/3 0:09 8.79% 8.79% ksh
>> 9 root 18 0 0K 40M syncer/3 0:07 0.00% 0.00% [ioflush]
>> 1590 hubertf 28 0 264K 1040K CPU/3 0:00 0.00% 0.00% top
...
> Interesting..
>
> Do you know why the top process appears on CPU/3 when dmesg and the
> top header agree that there is only CPU0 and CPU1?
No idea. Maybe someone on tech-kern@ (CC'd) knows?
- Hubert>
--
NetBSD - Free AND Open! (And of course secure, portable, yadda yadda)