Mike Christie wrote:
>> the noop-out based watch-dog serve all transports, correct?
> Yes

okay

>> narrow down things and understand if/what is the transport role:
> For the nop out path, the trasnport just has to send/recv the nop pdu/response

okay, fair-enough

> They do not have to make those calls for multipath to work. Multipath
> will work better if the transport can signal when there is a problem,
> because we can stop using a bad path and get IO going to a working path
> faster. If the transport does nothing then we have to rely on the scsi
> error handler/timeout to detect the problem and that is very slow.

I am still confused, in somehow black box manner, I understand and see (...) 
that:

A) the nop out based watch-dog serves all transports

B) if/when the transport doesn't signal to iscsi there's a problem with a 
session
multipathing works much more slower.

combining A && B I still don't see what is the exact role of the watch-dog, 
anyway,
maybe you should let me get some more millage on the thing and I'll get that...


> You should also change your ep_disconnect because it is not
> supposed to block (did we talk about this or was this just bnx2i), since
> it will stop iscsid from processing other events.

no, I didn't realized ep_connect shouldn't block up till we brought it here. 
Couples of years back when we did ep_connect/poll/disconnect we said that 
ep_connect initiates the connection establishment process and ep_poll reports 
about the progress. It turns out that I didn't pay attention to the price payed 
when ep_disconnect blocks. Let me take a look if I can just change it 
internally in iser or a patch to iscsi is needed, thanks for pointing this out!


Or.

-- 
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.

Reply via email to