On 02/02/2010 03:39 AM, Ulrich Windl wrote:
On 1 Feb 2010 at 11:52, Mike Christie wrote:
[...]
I was not sure though if I should check if any cmds to the target made
progress or if any cmds to the same disk. It could be that just one disk
went bad, so we might want to check per disk. However, this could be the
first IO to the disk and it just got stuck behind a bunch of other IO to
other disks, so in that case we want to check per target.
I'm no specialist on SCSI, but I think there is a "command abort" as
well as a "target abort" command. So when there are multiple
There is a abort_task which aborts one task. Then there is a
warm_target_reset and a cold_target_reset. They both basically abort all
the cmds on the target. For the target resets there are also other side
effects though.
outstanding commands, you should not abort the target as long as a
single command for that target is making any progress (and you should
re-arm the target abort timer (if such a thing exists)), but if none of
the commands for a specific target is making any progress, you should
either try a target abort or abort each command.
If a command times out we first try to abort each command with a
abort_task. If that fails we try a lun_reset to each device that had a
timed out command. If that fails we try a target_reset.
--
You received this message because you are subscribed to the Google Groups
"open-iscsi" group.
To post to this group, send email to [email protected].
To unsubscribe from this group, send email to
[email protected].
For more options, visit this group at
http://groups.google.com/group/open-iscsi?hl=en.
