Hedges, Richard M.
2013-Aug-23 18:49 UTC
Monitoring Lustre for health and user experience??
Can anyone point me to a study or anything from some site that has a story re monitoring/tracking Lustre for: * Basic health (to catch problems before users call) * Performance régressions due to software, hardware, etc. * Bad actors from the user community. Are there simple probes of Lustre health? * Are there metrics available from internal Lustre monitoring? * Even active probes such as running periodic benchmarks… Is there a relevant forum discussing this or related topics?? Thanks, - Richard =================================================== Richard Hedges Development Environment Group - Livermore Computing Lawrence Livermore National Laboratory 7000 East Avenue, MS L-557 Livermore, CA 94551 v: (925) 423-2699 f: (925) 423-6961 E: richard-hedges-i2BcT+NCU+M@public.gmane.org _______________________________________________ Lustre-discuss mailing list Lustre-discuss-aLEFhgZF4x6X6Mz3xDxJMA@public.gmane.org http://lists.lustre.org/mailman/listinfo/lustre-discuss
Apparently Analagous Threads
- Re: [zfs-discuss] ZFS/Lustre echo 0 >> max_cached_mb chewing 100% cpu
- build and install lustre from source code -- warning on livcfs.ko for no modversions
- Lustre build and install on Ubuntu
- Lustre 2.4 MDT: LustreError: Communicating with 0@lo: operation mds_connect failed with -11
- Quotas on Lustre File system