Hi, I'm having a peculiar "issue" in my cluster, which I'm not sure whether it's real: a particular OSD always shows significant latency in `ceph osd perf` report, an order of magnitude higher than any other OSD. I traced this OSD to a particular drive in a particular host. OSD logs don't look any different from any other OSD on the same node, iostat shows that the drive is utilized similarly to all other drives, the OSD process uses a similar amount of CPU and RAM to other OSD processes. I.e. the OSD and its underlying drive look the same as other OSDs and their drives and do not appear to have a higher latency on the host's system level. I am interested to find out what makes this OSD report much higher latency and what steps I could take to diagnose and troubleshoot this situation. I would appreciate any input and advice. Best regards, Zakhar _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |