Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 10 Mar 2005 22:32:09 +0800
From:      Dmitry Kozhevnikov <xeon@dsi.ru>
To:        freebsd-questions@freebsd.org
Subject:   Re[2]: Strange load averages on 5.3-STABLE
Message-ID:  <369266326.20050310223209@dsi.ru>
In-Reply-To: <42304CAC.1080203@tirloni.org>
References:  <42302BF1.70305@tirloni.org> <20050310131240.5ee338b5@montana.myrte.ma.cx> <20050310071851.D98716@grond.sourballs.org> <42304CAC.1080203@tirloni.org>

next in thread | previous in thread | raw e-mail | index | archive | help
please show us
1. cat /var/run/dmesg.boot
2. uname -a
3. egrep "(^REVISION|^BRANCH)" /usr/src/sys/conf/newvers.sh

GPT> David Fleck wrote:
>> On Thu, 10 Mar 2005, Michael Ross wrote:
>> 
>>>> last pid: 771; load averages: 176.65, 770.13, 926.55 up 0+00:03:13
>>>> 08:11:07
>>>>
>>> Your may have compiled kernel and userland from different sources.
>>> " and programs like ps(1) and top(1) will fail to work until the 
>>> kernel and source code versions are the same." from the handbook is
>>> what comes to my mind.

GPT>   I've compiled from the same source.

>> I've also seen ridiculously-high load numbers when NFS-mounted 
>> filesystems are inaccessible.  Usually that degrades system performance,
>> though.

GPT>   It's strange because everything is working fine and I don't use NFS on
GPT> it. For example, the load hits 900 and suddenly it's 3.








Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?369266326.20050310223209>