Description of problem: In NFS-Ganesha, a thread loops in continuously to poll for upcall events which may lead to 100% CPU usage. Fix has been provided in NFS-Ganesha upstream. Have to cherry-pick it to downstream build.
I now dont see the 100% CPU utilization, while IO going on on a ganesha volume : top - 20:53:40 up 15 days, 1:23, 6 users, load average: 1.90, 1.08, 0.55 Tasks: 281 total, 1 running, 280 sleeping, 0 stopped, 0 zombie Cpu(s): 4.3%us, 5.2%sy, 0.0%ni, 83.8%id, 6.3%wa, 0.0%hi, 0.3%si, 0.1%st Mem: 8059236k total, 2089396k used, 5969840k free, 183724k buffers Swap: 2097148k total, 0k used, 2097148k free, 1008748k cached PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 23462 root 20 0 2748m 189m 5792 S 17.6 2.4 0:48.20 ganesha.nfsd 31383 root 20 0 1882m 49m 4264 S 10.0 0.6 0:35.34 glusterfsd
Since the problem described in this bug report should be resolved in a recent advisory, it has been closed with a resolution of ERRATA. For information on the advisory, and where to find the updated files, follow the link below. If the solution does not work for you, open a new bug report. https://rhn.redhat.com/errata/RHSA-2015-1495.html