Mike Christie wrote:
> If we send too many nops marked as immediate we should be getting a 
> reject pdu right? If so then I think we just need the attached patch 
> which adds some code to handle rejected immediate pdus. The patch is 
> made over scsi-rc-fixes and is only compile tested.

I tested the patch and it should fix the problem where the connection 
was dropped because a nop was rejected and then we dropped the reject. I 
only tested the case where we sent too many nops as pings (I modified 
libiscsi to send a nop every second even if there were nops in flight 
already. I got floods of:

  connection1:0: pdu (op 0x455 itt 0x0) rejected. Too many immediate 

but the connect did not get dropped from our side because we did not get 
a nop in.

I did not test the case where the nop-out that was rejected was in 
response to a nop-in from the target. I could not replicate that one. 
But we would not have dropped the session in that case, so I do not 
think you were hitting that.

You received this message because you are subscribed to the Google Groups 
"open-iscsi" group.
To post to this group, send email to open-iscsi@googlegroups.com
To unsubscribe from this group, send email to 
For more options, visit this group at http://groups.google.com/group/open-iscsi

Reply via email to