Date: Mon, 21 Apr 1997 13:17:52 +0100 From: Alan Judge <Alan.Judge@indigo.ie> To: freebsd-scsi@freebsd.org Subject: Vendor specific ASCQ SCSI errors in 2.2-STABLE Message-ID: <199704211217.NAA20868@indigo.ie>
next in thread | raw e-mail | index | archive | help
[I'm not on the freebsd-scsi list, so please reply directly if you can
shed any light.]
I'm running 2.2-STABLE on a PPro machine with an Adaptec 3940UW and a bunch
of Quantum Atlas II disks. Tagging and SCB paging enabled.
I sometimes get errors of the form:
sd0(ahc0:0:0): ABORTED COMMAND asc:41,86 Vendor Specific ASCQ, retries:4
only under high load and on multiple different disks (as far as I can reproduce
the problem).
This sometimes results in errors like:
vnode_pager_putpages: I/O error 5
vnode_pager_putpages: residual I/O 4096 at 5816
and various sorts of crashes.
Can anyone tell me how to decode these?
I've got some docs from Quantum and they indicate that this error
is some sort of data path error, whatever that is.
I have a bunch of identical disks in a 2.2-GAMMA machine and have never seen
a similar error.
Any ideas?
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199704211217.NAA20868>