Date: Tue, 16 Apr 1996 19:50:06 -0700 From: David Greenman <davidg@Root.COM> To: Network Coordinator <nc@ai.net> Cc: "Marc G. Fournier" <scrappy@ki.net>, freebsd-questions@FreeBSD.ORG Subject: Re: Automatic Reboots and Locking up. Message-ID: <199604170250.TAA05027@Root.COM> In-Reply-To: Your message of "Tue, 16 Apr 1996 22:34:51 EDT." <Pine.BSF.3.91.960416222847.4115A-100000@aries.ai.net>
next in thread | previous in thread | raw e-mail | index | archive | help
>A few seconds before I got this output, the mbufs in use were over 1000,
>and the machine has only been on about 6 minutes. (Since the last time it
>hung on a reboot)
>
>813 mbufs in use:
> 543 mbufs allocated to data
> 262 mbufs allocated to packet headers
> 6 mbufs allocated to protocol control blocks
> 2 mbufs allocated to socket names and addresses
>523/726 mbuf clusters in use
^^^
You only care about this number. The number of mbufs in use is not
important to this problem - only the number of mbuf clusters.
>P.S. I also get an occasional error from the kernel "nfsd send error 55"
>can anyone tell me what error 55 is and what evil thingI must be doing to
>the machine to get it?
It's "no buffer space available". Do you use NFS heavily? If so, that could
be your problem. There are a variety of bugs in NFS that causes it to hang the
machine when used heavily. Casual use seems to be fine, it's only when
multiple processes start accessing files that it becomes a problem.
-DG
David Greenman
Core-team/Principal Architect, The FreeBSD Project
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199604170250.TAA05027>