Date: Thu, 17 Apr 2014 11:12:31 +0200 From: Robert Schulze <rs@bytecamp.net> To: freebsd-fs@freebsd.org Subject: Re: NFS behavior on a ZFS dataset with no quota remaining Message-ID: <534F9AFF.6010809@bytecamp.net> In-Reply-To: <21327.21004.879860.960260@hergotha.csail.mit.edu> References: <21327.21004.879860.960260@hergotha.csail.mit.edu>
next in thread | previous in thread | raw e-mail | index | archive | help
Hi, Am 17.04.2014 06:01, schrieb Garrett Wollman: > Recently one of our users managed to constipate one of our NFS servers > in an odd way. They hit the quota on their dataset, and rather than > having all of their writes error out as they should have, the NFS > server instead stopped responding to all requests. this behaviour is present since the beginnings of ZFS in FreeBSD. When a quota limit is reached, local reads are performing very bad or stall completely. The issue in combination with NFS is even more annoying, I've seen that happen quite often. IMHO this is a flaw which can easily be used to DOS any NFS server with quotas set. with kind regards, Robert Schulze -- /7\ bytecamp GmbH Geschwister-Scholl-Str. 10, 14776 Brandenburg a.d. Havel HRB15752, Amtsgericht Potsdam, Geschaeftsfuehrer: Bjoern Barnekow, Frank Rosenbaum, Sirko Zidlewitz tel +49 3381 79637-0 werktags 10-12,13-17 Uhr, fax +49 3381 79637-20 mail rs@bytecamp.net, web http://bytecamp.net/
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?534F9AFF.6010809>