Date: Wed, 13 Oct 2004 15:59:52 +0200 From: Martin Nilsson <martin@gneto.com> To: freebsd-hackers@freebsd.org Cc: sos@DeepCore.dk Subject: Re: ad0: FAILURE - WRITE_DMA Message-ID: <416D34D8.9050804@gneto.com> In-Reply-To: <200410131303.35695.miha@ghuug.org> References: <200410081937.15068.miha@ghuug.org> <200410091701.01987.miha@ghuug.org> <200410102330.26228.miha@ghuug.org> <200410131303.35695.miha@ghuug.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Mikhail P. wrote: > Well, now those timeouts popped up on 5.3-BETA7 system with 4 IDE drives.. > They start appearing with high disk activity. > System had FreeBSD-4.7 prior to that, and has been rock solid for almost a > year. Drives have no problems, that's for sure (4.7 did not show up any > timeouts, with uptime for months).. > > I don't know what to think - is ATA driver horribly broken in 5.x? Something is rotten with ATA on 5.x (or I have a rotten motherboard!) I have an E7320 "Lindenhurst VS ICH5R box" with 2*3GHz EM64T Xeons and 2*80GB Seagate SATA disks. Sometimes when booting the whole ATA/SATA system hangs after two READ_DMA or WRITE_DMA timeout errors. This seems to more common when running as AMD64 than i386. I can't remember any hangs after the machine have been up nicely for a couple of min. The 1U box is so noisy that I can't be in the apartment at the same time without going crazy, this and that I can't reproduce it reliably effectively prevents most debugging attempts. /Martin
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?416D34D8.9050804>