Hello Kilian, I am not entirely sure this is the same issue, but I know Prometheus doesn’t export some performance metrics by default anymore in Reef. This can be worked around by setting:
ceph config set mgr mgr/prometheus/exclude_perf_counters false A proper fix would be to switch to using a per-host ceph-exporter. Best regards, Pierre Riteau On Mon, 25 Nov 2024 at 13:45, Kilian Ries <m...@kilian-ries.de> wrote: > Prometheus metrics seem to be broken, too: > > > ceph_osd_op_r_latency_sum > > ceph_osd_op_w_latency_sum > > > Both of them for example are not reported by the ceph mgr metrics exporter: > > > curl http://192.168.XXX.XXX:9283/metrics |grep ceph_osd_ > > > > I get some merics like "ceph_osd_commit_latency_ms" or > "ceph_osd_apply_latency_ms" but none of the "op_r / op_w" metrics. Do the > lable names have switched and my grafana dashboard is outdated? Or are they > missing at the exporter level? > > > Thanks > > > > > ________________________________ > Von: Kilian Ries > Gesendet: Montag, 25. November 2024 13:37:16 > An: ceph-users@ceph.io > Betreff: AW: Ceph OSD perf metrics missing > > > Any ideas? Still facing the problem ... > > ________________________________ > Von: Kilian Ries > Gesendet: Mittwoch, 23. Oktober 2024 13:59:06 > An: ceph-users@ceph.io > Betreff: Ceph OSD perf metrics missing > > > Hi, > > > i'm running a Ceph v18.2.4 cluster. I'm trying to build some latency > monitoring with the > > > ceph daemon osd.4 perf dump > > > cli command. On most of the OSDs i get all the metrics i need. On some > OSDs i only get zero values: > > > osd.op_latency.avgcount: 0 > > > I already tried restarting the OSD process which didn't help. I also tried > to reset the metrics via > > > ceph daemon osd.4 perf reset all > > > but that didn't help either. How can that be that some OSDs don't show > values here? How can i fix that? > > > Thanks > > Regards, > > Kilian > _______________________________________________ > ceph-users mailing list -- ceph-users@ceph.io > To unsubscribe send an email to ceph-users-le...@ceph.io > _______________________________________________ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io
