Date: Thu, 04 Jul 2013 09:43:53 -0400 From: Travis Mikalson <bofh@terranova.net> To: freebsd-fs@FreeBSD.org Subject: Re: Report: ZFS deadlock in 9-STABLE Message-ID: <51D57C19.1080906@terranova.net> In-Reply-To: <51D5776F.5060101@FreeBSD.org> References: <51D45401.5050801@terranova.net> <51D5776F.5060101@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Andriy Gapon wrote: > on 03/07/2013 19:40 Travis Mikalson said the following: >> Hello, >> >> To cut to the chase, I have a procstat -kk -a captured during a livelock >> for you here: >> http://tog.net/freebsd/zfsdeadlock-storage1-20130703 > > BTW, https://wiki.freebsd.org/AvgZfsDeadlockDebug > > "If neither of the above is true. That is, you do see zio_wait and you don't see > either of zio_done or zio_interrupt, then the problem is most likely with the > storage layer..." Yes, that helpful article is where I got the run-down on how best to report what was going on here. I still believe this is an actual deadlock bug and not a storage layer issue. I have not seen any indications of any problems with my storage layer. You'd think there would be some scary-looking complaint on the console during one of these deadlocks if it had suddenly lost the capability to communicate with most or all the disks, but I've deadlocked at least 10 times now in 2013 and never anything of the sort. Thanks to IPMI, I have actually viewed the console each time it has happened.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?51D57C19.1080906>