Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 27 Nov 2009 10:31:02 -0800
From:      John Hickey <jhickey@ISI.EDU>
To:        "Bjoern A. Zeeb" <bz@FreeBSD.org>
Cc:        freebsd-bugs@FreeBSD.org, John Hickey <jhickey@ISI.EDU>
Subject:   Re: debugging a mbuf leak
Message-ID:  <20091127183101.GC29107@pod.isi.edu>
In-Reply-To: <20091126160522.T37440@maildrop.int.zabbadoz.net>
References:  <20091123213609.GD19973@pod.isi.edu> <20091126160522.T37440@maildrop.int.zabbadoz.net>

next in thread | previous in thread | raw e-mail | index | archive | help
Thanks for the reply.  We managed to track down the leak and have
submitted a PR (kern/140853) for it.

Thanks,
John

On Thu, Nov 26, 2009 at 04:07:26PM +0000, Bjoern A. Zeeb wrote:
> On Mon, 23 Nov 2009, John Hickey wrote:
>
> Hi John,
>
>> One of our main servers here has a slow mbuf leak.  We are not sure what
>> is causing it at this point.  Does anyone have some pointers on how to
>> dig further into this?
>
> There are a couple of things to check:
> 1) is it really a leak?
>
>    This can easily be tested by going down to single user and see
>    if the mbufs got freed again.
>
> 2) maybe starting with this first: which version of freebsd is this?
>
>
>> Mon Nov 23 13:19:15 PST 2009
>>
>> 16364/2836/19200 mbufs in use (current/cache/total)
>> 928/2216/3144/132096 mbuf clusters in use (current/cache/total/max)
>> 512/1664 mbuf+clusters out of packet secondary zone in use
>> (current/cache)
>> 0/135/135/66048 4k (page size) jumbo clusters in use
>> (current/cache/total/max)
>> 0/0/0/33024 9k jumbo clusters in use (current/cache/total/max)
>> 0/0/0/16512 16k jumbo clusters in use (current/cache/total/max)
>> 5947K/5681K/11628K bytes allocated to network (current/cache/total)
>> 0/0/0 requests for mbufs denied (mbufs/clusters/mbuf+clusters)
>> 0/0/0 requests for jumbo clusters denied (4k/9k/16k)
>> 0/5/33280 sfbufs in use (current/peak/max)
>> 0 requests for sfbufs denied
>> 0 requests for sfbufs delayed
>> 0 requests for I/O initiated by sendfile
>> 0 calls to protocol drain routines
>>
>> Mon Nov 23 13:24:21 PST 2009
>>
>> 18085/2660/20745 mbufs in use (current/cache/total)
>> 923/2455/3378/132096 mbuf clusters in use (current/cache/total/max)
>> 512/1664 mbuf+clusters out of packet secondary zone in use
>> (current/cache)
>> 0/135/135/66048 4k (page size) jumbo clusters in use
>> (current/cache/total/max)
>> 0/0/0/33024 9k jumbo clusters in use (current/cache/total/max)
>> 0/0/0/16512 16k jumbo clusters in use (current/cache/total/max)
>> 6367K/6115K/12482K bytes allocated to network (current/cache/total)
>> 0/0/0 requests for mbufs denied (mbufs/clusters/mbuf+clusters)
>> 0/0/0 requests for jumbo clusters denied (4k/9k/16k)
>> 0/5/33280 sfbufs in use (current/peak/max)
>> 0 requests for sfbufs denied
>> 0 requests for sfbufs delayed
>> 0 requests for I/O initiated by sendfile
>> 0 calls to protocol drain routines
>>
>> _______________________________________________
>> freebsd-bugs@freebsd.org mailing list
>> http://lists.freebsd.org/mailman/listinfo/freebsd-bugs
>> To unsubscribe, send any mail to "freebsd-bugs-unsubscribe@freebsd.org"
>>
>
> -- 
> Bjoern A. Zeeb         It will not break if you know what you are doing.



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20091127183101.GC29107>