Hi, We are using EC profile in our cluster. We are seeing very high RAM usage in 1 OSD server. Sometimes it goes too low and server hangs. We have to restart the daemons which frees up the memory, but in very short time get used up again
Memory usage of daemons from issue server ------------- PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 16918 ceph 20 0 15.780g 0.013t 7928 S 28.2 21.9 67:29.09 ceph-osd 18568 ceph 20 0 25.833g 0.023t 26096 S 24.9 36.8 9:15.58 ceph-osd 22630 ceph 20 0 12.520g 0.011t 26660 S 22.3 18.3 5:49.03 ceph-osd 2796 ceph 20 0 11.091g 9.851g 8900 S 13.6 15.7 25:17.68 ceph-osd Memory usage from another server : ------------------------------- PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 11649 ceph 20 0 12.788g 9.563g 25068 S 107.6 7.6 12285:54 ceph-osd 18295 ceph 20 0 11.028g 6.069g 26212 S 54.0 4.8 2122:18 ceph-osd 30974 ceph 20 0 13.860g 0.010t 24956 S 46.4 8.1 10984:47 ceph-osd We are using ec profile 5/3. And there are 2 failed disks in the cluster in another nodes, (I have marked them down, but not out) so cannot turn this node off as it will force some pgs to be incomplete state. And help would be really appreciated. Karun Josy
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
