ia64_corehw using 90-100% of a cpu

[S.Rider]

We'running EMS A.04.00.02 / Online Diag B.11.11.15.13 / ISEE A.03.90.872 on a bunch of HPUX 11.11 systems. On 3 systems running as vPars in a nPar which is in the Superdome expansion cabinet, the ia64_corehw process is taking up almost all of one of each vpar's cpus. Nothing exciting in syslog.log. No recent errors in cstm log. No recent ISEE alerts. No defunct processes spawned off ia64_corehw. Anyone know how to figure out what this guy thinks he's doing ?

[Jean-Luc Oudart]

Hi

you may check this thread :
http://forums1.itrc.hp.com/service/forums/questionanswer.do?threadId=837725

Regards
Jean-Luc

[S.Rider]

The earlier thread seems to address an issue with a child process being started by ia64_corehw that appears defunt after a while, but a new child ia64_corehw process keeps getting started with a different pid.
My ia64_corehw child process is started once and runs forever accumulating an impressive total of cpu minutes by the next day.
I opened a call with the HP Response Centre also and that's the first thing they asked "got any defunct processes".

[Andrew Merritt_2 · Accepted solution]

Hi Jay,
There is a known problem on vPar systems where this can happen. The defect is somewhere in either or both of the vpar software and firmware; HP is working on a fix.

Upgrading to the 3.1 firmware package seems to fix this in at least some cases (this upgrade actually involves a CoreIO downgrade from 2.009 to 2.008, since there is a problem in 2.009).

Without a firmware upgrade, taking the complex down is necessary to clear the problem; restarting the OnlineDiags is not enough, and it may then still recur.

A short term work-around would be to disable the monitor on affected partitions.

1. Login as user root.

2. Run monconfig:
# /etc/opt/resmon/lbin/monconfig

3. Select:
(K)ill (disable) monitoring
(Q)uit

4. Move the executable for the daemon to directory org. We can
restore the monitor if necessary by moving the executable back.

# cd /usr/sbin/stm/uut/bin/tools/monitor
# mkdir org
# mv ia64_corehw org

5. Move the dictionary entry to the directory org.
We can restore the monitor if necessary by moving the file back.

# cd /etc/opt/resmon/dictionary
# mkdir org
# mv ia64_corehw.dict org

6. Remove the .hwa file. The file will be recreated automatically
if all monitor files are copied back and the monitor is restarted.

# cd /var/stm/data/tools/monitor
# rm ia64_corehw.hwa

7. Move the startup, configuration and psm files to the directory org.

# cd /var/stm/config/tools/monitor
# mkdir org
# mv *ia64_corehw.* org

8. Run monconfig again:
# /etc/opt/resmon/lbin/monconfig
Select
(E)nable Monitoring
(Q)uit

9. Verify that the monitor is not running any more:
# ps -ef | grep ia64_corehw



Andrew

[Andrew Merritt_2]

Just to make things clear, in case I wasn't, this has nothing at all to do with the 'defunct' process.

If you're talking to HP support, point them at CR JAGaf74402.

Andrew

[S.Rider]

We're upgrading the vPar software to A.03.03 this weekend to take care of the issue for good.