i'm not using multipath, and it seems that i have the exact same problem.
(identical ietd version, debian squeeze on amd64, open-iscsi as initiator)
when i restart ietd during i/o, the session on the initiator side goes unsuable
readonly, with no way to get it working other than logout/login
On 06/11/2012 07:43 AM, niejasiek wrote:
i'm not using multipath, and it seems that i have the exact same problem.
(identical ietd version, debian squeeze on amd64, open-iscsi as initiator)
when i restart ietd during i/o, the session on the initiator side goes
unsuable
readonly, with no
On 06/08/2012 11:10 PM, Anish Bhatt wrote:
Mike,
Has there been any progress in figuring out how DCB would
co-exist with net prio cgroups since you removed DCB support ?
-Anish
I think people were saying to do something with cgdcbxd.
Are you guys using DCB with iSCSI for software
I was looking at support for cxgb*i, since open-iscsi previously only
had DCB support for the software initiator. I'm guessing with cgdcbxd
the task of looking up cgroup and assigning priority to the traffic is
left to the individual transports now ?
-Anish
One socket to bind them all.
On 06/11/2012 06:08 PM, Anish Bhatt wrote:
I was looking at support for cxgb*i, since open-iscsi previously only
had DCB support for the software initiator. I'm guessing with cgdcbxd
the task of looking up cgroup and assigning priority to the traffic is
left to the individual transports now ?
We're doing it in firmware as well, since it already has all DCB info. I
was just checking if there was any plan to make the transports interact
with cgroups in a uniform way, as previously DCB was left upto
individual implementations. Guess not.
-Anish
One socket to bind them all.
