On 10/9/2014 8:14 AM, Jayamohan.K wrote:
<SNIP>
Hi Minh and Jayamohan,
So I agree that we would want to take device capabilities into account
here, but we need to be able to adjust scsi_cmds_max (can_queue) in case
the max wqe supported is lower than scsi_cmds_max * num_posts_per_cmd.
I feel we should be fine as long as we support the max_cmds of 128
supported by open-iscsi layer.
The cmds_max can be modified by the user, so we should be fine in this
case as well.
I see the iser layer uses a value of 512 though it only serves as a
limit check.
So if iser supports less than 512 (due to device capability) the
boundary check should be modified as well.
So generally I agree with this approach, but we need to take care of
stuff later when the session is created.
One more thing, this is not rebased on the latest iser patches please
send v1 on top of:
http://marc.info/?l=linux-__rdma&m=141216135013146&w=2
<http://marc.info/?l=linux-rdma&m=141216135013146&w=2>
Yes, I will recreate the patch and send on top of this
Great!
P.S.
What device did you test with (that supports less than iSER needs)?
This question still holds.
Sagi.
--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
