Red Hat Bugzilla – Bug 217246
iscsid floods target with nop outs
Last modified: 2007-11-30 17:07:38 EST
Description of problem:
Possible RHEL4/3 regression.
iscsid does not wait for a nop-out response before sending another one. This
then floods the target and the netlink interface with nop-out responses from the
target. And this prevents errors from the kernel from getting handled in a
timely manner and then causes problems with multipath and clustering software.
Version-Release number of selected component (if applicable):
Steps to Reproduce:
node.conn.timeo.noop_out_interval = 5
(this was the RHEL4 Active Ping interval)
run on a slow connection and watch "iscsid -d 8" or tcpdump/ethereal for a flood
of nop outs sent to the target.
iscsid also marks every nop as immediate. Some targets can only handle one
immediate request at a time, so this can result in different errors and problems
depending on the target.
This request was evaluated by Red Hat Product Management for inclusion in a Red
Hat Enterprise Linux major release. Product Management has requested further
review of this request by Red Hat Engineering, for potential inclusion in a Red
Hat Enterprise Linux Major release. This request is not yet committed for
QE ack for RHEL5.
A package has been built which should help the problem described in
this bug report. This report is therefore being closed with a resolution
of CURRENTRELEASE. You may reopen this bug report if the solution does
not work for you.