Hi, all I've started use Ceph on a small production enviroment for a couple of weeks. And I've learned to use commands like 'ceph osd perf' and 'ceph --admin-daemon ... perf dump' to find latency information about my cluster. However, I don't quite understand the exact meaning of those performance values, for example, 'fs_commit_latency', 'fs_apply_latency', 'op_*_latency' and 'subop_*_latency'. Is there any documents that explain what those latencies measured along Ceph's I/O Path. Thanks, Jianing Yang -- _____________________________________ / The powernap package allows you to \ | suspend servers which are not being | | used, and save energy. | \ https://launchpad.net/powernap / ------------------------------------- \ \ \ .- <O> -. .-====-. ,-------. .-=<>=-. /_-\'''/-_\ / / '' \ \ |,-----.| /__----__\ |/ o) (o \| | | ')(' | | /,'-----'.\ |/ (')(') \| \ ._. / \ \ / / {_/(') (')\_} \ __ / ,>-_,,,_-<. >'=jf='< `. _ .' ,'--__--'. / . \ / \ /'-___-'\ / :| \ (_) . (_) / \ / \ (_) :| (_) \_-----'____--/ (_) (_) (_)_______(_) |___:|____| \___________/ |________| \_______/ |_________| _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |