Date: Wed, 12 Dec 2001 21:44:56 +0200 From: Alex Popa <razor@ldc.ro> To: Morsal Roudbay <morsal@swipnet.se> Cc: Brady Montz <bradym@mail.hydrologue.com>, stable@FreeBSD.ORG Subject: Re: 4.4-STABLE crashes - suspects new ata-driver over wd-driver Message-ID: <20011212214455.C10147@ldc.ro> In-Reply-To: <20011210184258.GC25562@zigman.2y.net>; from morsal@swipnet.se on Mon, Dec 10, 2001 at 07:42:58PM %2B0100 References: <200112050033.fB50X6G12476@mail.hydrologue.com> <20011210184258.GC25562@zigman.2y.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, Dec 10, 2001 at 07:42:58PM +0100, Morsal Roudbay wrote: > On Tue, Dec 04, 2001 at 04:33:06PM -0800, Brady Montz wrote: > > Morsal Roudbay <morsal@swipnet.se> writes: > > > > > On Sat, Dec 01, 2001 at 02:45:18AM -0500, Chris BeHanna wrote: > > I've been recently noticing the same thing with my machine. I don't > > have the specs handy since I'm at work, but I am using IDE drives. > > The trouble started last week, using a 4.4-STABLE kernel built on Nov 3. > > I reinstalled world yesterday from the latest 4.4-STABLE, > > and it hasn't gotten better. > > > > For me, it only happens during heavy disk access, such as when backing > > up my hard drive to a huge tar file, or when doing build or clean. My > > machine will either lock up or reboot. I haven't seen any messages in > > any of my log files. The MTBF under such load (like portupgrade mozilla) seems > > to be about an hour or so. > > > > Other data poiints: I ran memtest86 overnight, and it didn't find any > > memory errors, and tripwire hasn't noticed any filesystem corruption. > > I ran some checks on my harddrives (IDE ones) and RAM, no indications of failure. > > If I upgrade several ports at the same time the machine shuts down. > > This sever of mine worked very well before the upgrade to 4.4-STABLE. > > Morsal I still have the same kernel I reported the freezes with, but for now the machine has been running for about 8 days, without crashes. I even ran bonnie++ over the weekend. It ran on the partition (actually vinum mirrored volume) on which the system was writing when I had the initial crashes. Arguments to bonnie++ were "-s 3g -n 128:16384:0:16". I ran bonnie++ twice, first on the volume w/o softupdates, then w/ softupdates, and I got no crashes. During the bonnie++ runs iostat showed some 22M/s activity on each disk, so I am beginning to suspect there has to be a correlation between heavy disk I/O and heavy network I/O (my initial crashes occured when someone was making a large backup over SMB to the server, at about 9M/s disk activity) in order to get the crashes. Also there might be something wrong with some part of the disks, because when running bonnie++, the disks were about 12G more occupied. Again, I am running 4.4-RELEASE, kernel config is based on GENERIC, but only with 686 CPU support, maxusers 128, no INET6, with IPFILTER, no SCSI, no pccard. The next thing I am going to try (when I get physically to the server) is to run bonnie++ in conjunction with some TCP/IP stress, first over loopback, then over ethernet. Have Fun! ------------+------------------------------------------ Alex Popa, | "Artificial Intelligence is razor@ldc.ro| no match for Natural Stupidity" ------------+------------------------------------------ "It took the computing power of three C-64s to fly to the Moon. It takes a 486 to run Windows 95. Something is wrong here." To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20011212214455.C10147>