From: Greg Banks Subject: Re: NFSERR_NOSPC nfs-client bug Date: Tue, 18 Mar 2008 13:08:21 +1100 Message-ID: <47DF2415.6070802@melbourne.sgi.com> References: <200803172021.08327.nfs@share-foo.com> <47DF1E5C.9090607@melbourne.sgi.com> <200803172050.22223.nfs@share-foo.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Cc: linux-nfs@vger.kernel.org To: nfs-Uh4cUGhLB8SgSpxsJD1C4w@public.gmane.org Return-path: Received: from netops-testserver-3-out.sgi.com ([192.48.171.28]:53825 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751882AbYCRCEg (ORCPT ); Mon, 17 Mar 2008 22:04:36 -0400 In-Reply-To: <200803172050.22223.nfs-Uh4cUGhLB8SgSpxsJD1C4w@public.gmane.org> Sender: linux-nfs-owner@vger.kernel.org List-ID: Ray Ferguson wrote: > On Monday 17 March 2008 20:43, Greg Banks wrote: > >> It doesn't ignore ENOSPC, it reports it on close(). Of course this is >> often several gigabytes of lost data too late. >> > > In our case, the thrashing it gave our Linux NFS cluster was severe enough to > take it out of commission. The lost data from the file transfer that > triggered the event was the least of our worries. > > Agreed, it sucks. -- Greg Banks, R&D Software Engineer, SGI Australian Software Group. The cake is *not* a lie. I don't speak for SGI.