Date: Wed, 15 Sep 1999 01:17:26 -0700 From: Don Lewis <Don.Lewis@tsc.tdk.com> To: Andrew Gallatin <gallatin@cs.duke.edu>, "Justin T. Gibbs" <gibbs@caspian.plutotech.com> Cc: scsi@FreeBSD.ORG, anderson@cs.duke.edu, Don Lewis <Don.Lewis@tsc.tdk.com> Subject: Re: data corruption when using aic7890 Message-ID: <199909150817.BAA17039@salsa.gv.tsc.tdk.com> In-Reply-To: Andrew Gallatin <gallatin@cs.duke.edu> "Re: data corruption when using aic7890" (Sep 13, 11:45am)
next in thread | previous in thread | raw e-mail | index | archive | help
On Sep 13, 11:45am, Andrew Gallatin wrote: } Subject: Re: data corruption when using aic7890 } } I've tried all the extremes, with the following results: } } RD_DFTHRSH_MAX | WR_DFTHRSH_MIN: corruption on read soon after first pass } RD_DFTHRSH_MIN | WR_DFTHRSH_MIN: corruption on read soon after first pass } RD_DFTHRSH_MAX | WR_DFTHRSH_MAX: immediate corruption (maybe write was corrupted?) } RD_DFTHRSH_MIN | WR_DFTHRSH_MAX: immediate corruption (maybe write was corrupted?) It looks like this problem is not affected by the setting of RD_DFTHRSH and is affected by the setting of WR_DFTHRSH. Too bad neither extreme setting is error free. According to Justin's comment, this knob controls the behavior of writes by the adapter to memory (disk reads). I wonder if it might be botching PCI MWI transactions. Is there a way to get this beast to just use plain PCI Memory Write transactions (with the obvious performance penalty)? To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199909150817.BAA17039>