perfSONAR User Q&A and Other Discussion

[Sean Crosby <>]

Hi,

I'm noticing quite a lot of zombie processes on our latency node since the upgrade to 3.4.

The zombie processes are all powstream processes

[root@ps-latency ~]# ps aux | awk '{ print $11 " " $8 " " $2 }' | grep Z

[powstream] Zs 12250

[powstream] Zs 15773

[powstream] Zs 15784

[powstream] Zs 17539

[powstream] Zs 24119

[powstream] Zs 24131

[powstream] Zs 25685

[powstream] Zs 26362

[powstream] Zs 35252

[powstream] Zs 37040

[powstream] Zs 43496

[powstream] Zs 44754

[powstream] Zs 45289

[root@ps-latency ~]# rpm -qa | grep owamp

owamp-3.4-6.x86_64

owamp-server-3.4-10.el6.x86_64

owamp-client-3.4-10.el6.x86_64

Is this a known issue? I last rebooted the host around 10 days ago due to the same problem. I don't see any zombie processes on our bandwidth node, so it just looks like a owamp problem.

Cheers,

Sean

--

Sean Crosby

Research Computing System Administrator and Developer

ARC Centre of Excellence for Particle Physics at the Terascale

School of Physics | University of Melbourne Vic 3010

T: +61 3 8344 8093