Date: Thu, 22 Aug 2013 14:41:19 +0200 From: =?iso-8859-2?Q?Edward_Tomasz_Napiera=B3a?= <trasz@FreeBSD.org> To: Konstantin Belousov <kostikbel@gmail.com> Cc: freebsd-fs@freebsd.org Subject: Re: 9.2-RC1: LORs / Deadlock with SU+J on HAST in "memsync" mode Message-ID: <23FCE234-E811-4160-BCDD-B0E2B832DCD3@FreeBSD.org> In-Reply-To: <20130822093138.GO4972@kib.kiev.ua> References: <20130819115101.ae9c0cf788f881dc4de464c5@yamagi.org> <20130822102121.a799b116b0f6b0f7c90ba578@yamagi.org> <20130822093138.GO4972@kib.kiev.ua>
next in thread | previous in thread | raw e-mail | index | archive | help
Wiadomo=B6=E6 napisana przez Konstantin Belousov w dniu 22 sie 2013, o = godz. 11:31: > On Thu, Aug 22, 2013 at 10:21:21AM +0200, Yamagi Burmeister wrote: >> Hello, >> attached is a file with the transcript of a dd session containing: >> - ps >> - trace >> - show pcpu >> - show allpcpu >> - show locks >> - show alllocks >> - show lockedvnods >> - alltrace >> If the attachement is eaten by mailman the file can be found here: >> http://deponie.yamagi.org/freebsd/debug/lor_hast/ddb2.txt >>=20 >> This is my first deadlock debug session. So if anything is still >> missing please tell me. >>=20 > This has absolutely nothing to do with the deadlock we trying to = catch. > On your case, it seems that all i/o on the box is stalled, and my = guess > is that hastd just recursed waiting for some i/o completion which = requires > working hastd to finish. >=20 > Talk to hastd author(s) about this. Isn't this just another case of deadlock caused by being out of bufs? --=20 If you cut off my head, what would I say? Me and my head, or me and my = body?
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?23FCE234-E811-4160-BCDD-B0E2B832DCD3>