[LU-9957] Some LNet warning message caused by running IOR

Wed, 21 Mar 2018 16:44:08 +0000

Hi All,

We have used IOR to stress our Lustre file system that includes 4 X OSS servers and 1X MGS/MDS server. After running a few hours, some LNet warning messages listed below are found in /var/log/messages.

Please kindly give us some suggestions for how to debug our Lustre file system.

Thanks a lot!

===================================================================
Sep 7 21:00:59 oss1 kernel: LNet: Service thread pid 25482 completed after 41.14s. This indicates the system was overloaded (too many service threads, or there were not enough hardware resources).
Sep 7 21:22:03 oss1 kernel: LNet: Service thread pid 1088 completed after 67.46s. This indicates the system was overloaded (too many service threads, or there were not enough hardware resources).
Sep 7 21:36:50 oss1 kernel: LNet: Service thread pid 21711 completed after 52.04s. This indicates the system was overloaded (too many service threads, or there were not enough hardware resources).
Sep 7 22:20:42 oss1 kernel: LNet: Service thread pid 28459 completed after 22.70s. This indicates the system was overloaded (too many service threads, or there were not enough hardware resources).
Sep 7 22:41:20 oss1 kernel: LNet: Service thread pid 2743 completed after 52.61s. This indicates the system was overloaded (too many service threads, or there were not enough hardware resources).
Sep 7 23:51:26 oss1 kernel: LNet: Service thread pid 406 completed after 50.76s. This indicates the system was overloaded (too many service threads, or there were not enough hardware resources).
Sep 8 00:30:52 oss1 kernel: LNet: Service thread pid 885 completed after 23.67s. This indicates the system was overloaded (too many service threads, or there were not enough hardware

Whamcloud Community JIRA

[LU-9957] Some LNet warning message caused by running IOR