Date: Mon, 20 Apr 2009 22:14:53 -0400 From: Ryan Stone <rysto32@gmail.com> To: Tom McLaughlin <tmclaugh@sdf.lonestar.org> Cc: current@freebsd.org Subject: Re: NFS lockd/statd lock up network connection Message-ID: <bc2d970904201914y3ea5e6ccj7491d011299b4138@mail.gmail.com> In-Reply-To: <49EBC778.7080305@sdf.lonestar.org> References: <49D851FC.4090103@sdf.lonestar.org> <bc2d970904081505m7ae99eaft75bdd908ba2f4b49@mail.gmail.com> <bc2d970904081512l66fd6da9xba84886cd49bab40@mail.gmail.com> <49EBC778.7080305@sdf.lonestar.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Well, that does confirm that your system is running out of clusters. Because you lose all network connectivity I'd suspect a leak, probably in code exercised by lockd. I'm afraid that I know absolutely nothing about it so I can't offer any kind of solution. Hopefully somebody who does know something is paying attention. One thing you could try is setting the tunable kern.ipc.nmbclusters higher than 25600 -- maybe 40000? If it's a leak that won't help anything but if your system just doesn't have enough clusters that will fix it.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bc2d970904201914y3ea5e6ccj7491d011299b4138>