Date: Fri, 10 Feb 2012 11:19:28 +0100 From: Peter Maloney <peter.maloney@brockmann-consult.de> To: freebsd-fs@freebsd.org Subject: Re: zfs snapdir NFS hang Message-ID: <4F34EF30.1030706@brockmann-consult.de> In-Reply-To: <4F33E952.80102@brockmann-consult.de> References: <4F33CA4D.6060400@brockmann-consult.de> <4F33E952.80102@brockmann-consult.de>
next in thread | previous in thread | raw e-mail | index | archive | help
On 02/09/2012 04:42 PM, Peter Maloney wrote: > ... > And for the record, I have tested full scans of the .zfs/snapshot > directory using "find" to see if it "brings the server to its knees" as > is often said, but even that does not cause any problems at all (with 48 > GB of memory on this machine). I am currently running another run of > that test, and will tell you the result in 20 or so hours when it is done. > > # time find /tank/bcnasvm1/.zfs/snapshot -type f > /dev/null 2>&1 The result was that the system seemed fine, for a while, but after fiddling with NFS and snapshots, eventually every new process (eg. a local login on the machine terminals) would be killed with a message about being out of swap space. I guess it can only eat all your memory when you have more data or snapshots, because fun stuff like this didn't happen before. Or perhaps I didn't catch it before, because I didn't try fiddling with other things the last time I tested it.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4F34EF30.1030706>