Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 9 Jul 2008 22:09:35 -0400
From:      John Baldwin <jhb@FreeBSD.org>
To:        gnn@FreeBSD.org
Cc:        freebsd-current@FreeBSD.org
Subject:   Re: Has anyone else seen any form of in memory or on disk corruption?
Message-ID:  <200807092209.35780.jhb@freebsd.org>
In-Reply-To: <m2prpss3xn.wl%gnn@neville-neil.com>
References:  <m2r6a9poww.wl%gnn@neville-neil.com> <200807041521.25711.jhb@freebsd.org> <m2prpss3xn.wl%gnn@neville-neil.com>

next in thread | previous in thread | raw e-mail | index | archive | help
On Saturday 05 July 2008 12:15:16 pm gnn@freebsd.org wrote:
> At Fri, 4 Jul 2008 15:21:25 -0400,
> John Baldwin wrote:
> > 
> > If this is one of the ATA controllers where it tries to use 63k
> > transfers (126 * DEV_BSIZE) instead of 64k, then change it to 32k
> > (64 * DEV_BSIZE).  W/o this fix I see massive data corruption
> > (couldn't even build a kernel with the fix, had to reinstall the
> > box) on HT1000 ATA chipsets.  Crashdumps also don't seem to work
> > reliably w/o changing that.
> > 
> 
> Hmm, I don't see quite that much corruption.
> 
> Reading over ata-chipset.c I see that there are 4 controllers which
> may have this issue:
> 
> Cyrix
> Marvell
> National
> Serverworks
> 
> This has been happening on AMCC cards and very occasionally Supermicro
> motherboards.  Is there an easy way to determine if either of those
> are using these chips?

PCI device IDs of the atapciX devices (and see if they match up with what 
devices use the chipset routines that set '126 * DEV_BSIZE'

-- 
John Baldwin



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200807092209.35780.jhb>