Date: Thu, 27 Nov 2003 12:04:51 +0100 From: =?iso-8859-2?q?S=B3awek_=AFak?= <szak@era.pl> To: =?iso-8859-2?q?S=B3awek_=AFak?= <szak@era.pl> Cc: freebsd-current@freebsd.org Subject: Re: UFS lockups Message-ID: <86isl6xeb0.fsf@thirst.unx.era.pl> In-Reply-To: <867k1n16zd.fsf@thirst.unx.era.pl> =?iso-8859-2?q?=28S=B3awek's?= message of "Wed, 26 Nov 2003 16:31:50 %2B0100") References: <867k1n16zd.fsf@thirst.unx.era.pl>
next in thread | previous in thread | raw e-mail | index | archive | help
--=-=-=
Content-Type: text/plain; charset=iso-8859-2
Content-Transfer-Encoding: 8bit
Sławek Żak <szak@era.pl> writes:
> I observe UFS lockups under heavy I/O. To reproduce the problem run around
> 10 copies of cp -Rp /usr/some-random-dir. All cp's after some time are hanging
> on getblk. du's running concurrently are hanging in ufs state. The filesystems
> are UFS2. The Server is running 5.2-BETA on SMP Dell 2650. Filesystems are laid
> on Adaptec RAID controller (aac). Any ideas how to trace the problem?
I managed to obtain trace of one of the processes hung in the ufs
state. Sorry for the form, I can't make a text dump of the messages.
/S
--=-=-=--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?86isl6xeb0.fsf>