Date: Wed, 17 Dec 2014 12:13:02 -0800 From: Daniel Andersen <dea@caida.org> To: Michael Ranner <michael@ranner.eu>, freebsd-fs@freebsd.org Subject: Re: Process enters unkillable state and somewhat wedges zfs Message-ID: <5491E3CE.2030003@caida.org> In-Reply-To: <549152B5.6030100@ranner.eu> References: <549152B5.6030100@ranner.eu>
next in thread | previous in thread | raw e-mail | index | archive | help
I'm certainly not an expert on this, but from my understanding, I think Andriy Gapon had some thoughts on this particular problem and potential solutions: http://lists.freebsd.org/pipermail/freebsd-fs/2014-November/020482.html At least, I think these problems are related. >From my end, my 'solution' was to stop using nullfs mounts in conjunction with zfs. :( Fortunately, our jail servers don't use zfs, yet. Since I reorganized our data NFS server to stop using nullfs, it's been very stable. ( aside from one crash when it's raid 1 boot drive somehow went offline.. but I'm fairly sure that had nothing whatsoever to do with the ZFS problems. ) Dan On 12/17/2014 01:53 AM, Michael Ranner wrote: > Hello there! > > I have the same problem on FreeBSD 9.3-RELEASE-p6. > > mount_nullfs of ZFS dataset in jail environment. > > php-fpm process get stuck (100% CPU, unkillable) and the specific ZFS dataset is unaccessible. Further processes > accessing the same dataset are hanging in state zfs. > > Other datasets on the same pool are still accessible. > > The stack trace looks very similar to Daniels. > > Is there any progress on this? > > I have many very similar environments (jail, ZFS, nullfs mounts), so I am interested in some solution or workaround. > > -- > Mit freundlichen Grüßen > > Ing. Michael Ranner > > GSM: +43 676 4155044 > Mail: michael@ranner.eu > WWW: http://www.azedo.at/ >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?5491E3CE.2030003>