Date: Mon, 13 Dec 1999 07:30:13 +0800 From: Peter Wemm <peter@netplex.com.au> To: mauzi@poli.hu Cc: Julian Elischer <julian@whistle.com>, freebsd-hackers@FreeBSD.ORG Subject: Re: silo overflows Message-ID: <19991212233013.EE2921CA0@overcee.netplex.com.au> In-Reply-To: Message from Julian Elischer <julian@whistle.com> of "Sun, 12 Dec 1999 15:06:54 PST." <Pine.BSF.4.10.9912121324200.26823-100000@current1.whistle.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Julian Elischer wrote: > > > On Sun, 12 Dec 1999, Gergely EGERVARY wrote: > > > > what kind of disk to you have? and the chipset? (this may seem irrelevant > > > but misconfigured DMA devices can block the cpu for long enough to cause > > > this sort of thing in some cases). ALSO check systat -vmstat while this > > > is happenning and check that you don't have a source of spurious > > > interrupts. > > > > > > Julian > > > > intel 440bx chipset (abit-bh6 mainboard) > > quantum cx13.0a ata4 disk > > > > actually i don't see any spurious interrupts :) > > (that had happenned to me) > > If you can get the disk working right it may even solve the silo problem. > (it did for me) > It turned out that the disk system was blocking the PCI bus during DMA > > Julian For what it's worth, your problem is a wdc driver and/or a configuration problem. outback# dd if=/dev/ad0s1b of=/dev/null bs=256k count=512 512+0 records in 512+0 records out 134217728 bytes transferred in 6.868476 secs (19541122 bytes/sec) That's a 440bx and a quantum cx drive (slightly smaller, 10MB), but under -current. You have remembered to set flags 0xa0ffa0ff on the wdc controller right? Cheers, -Peter To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19991212233013.EE2921CA0>