Date: Tue, 9 Sep 1997 23:20:03 +0200 From: Stefan Esser <se@FreeBSD.ORG> To: Terry Lambert <tlambert@primenet.com> Cc: Mats Lofkvist <mal@algonet.se>, current@FreeBSD.ORG Subject: Re: lousy disk perf. under cpu load (was IDE vs SCSI) Message-ID: <19970909232003.34238@mi.uni-koeln.de> In-Reply-To: <199709091834.LAA28493@usr04.primenet.com>; from Terry Lambert on Tue, Sep 09, 1997 at 06:34:13PM %2B0000 References: <199709091225.OAA14331@kairos> <199709091834.LAA28493@usr04.primenet.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sep 9, Terry Lambert <tlambert@primenet.com> wrote: > > But can lack of tagged command queueing explain the combination of good > > performance unloaded and bad with one or more cpu bound processes? > > Yes, I believe so: swapping. But you need to know for sure if it > is supported in your version, and I'm not the one to ask. Look > at the archives, or wait for Stefan to post. Well, as I always wrote in another message, the NCR driver supports tags for more than 3 years, already ... > > I have no problem with issues with the 810a affecting devices connected > > to it, but is it probable it could affect devices connected to the adaptec? > > No. The problems were specific to the 810a. There is a restriction with the alignment of data moved from memory to memory by the NCR under very specific circumstances (which depend on the chip set and PCI BIOS). But if your chip had that problem and it was not fixed in the driver, the system would fail to boot at all ... Regards, STefan
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19970909232003.34238>