Hi all, I have flaky transceivers that sometimes lead to these messages:
Slow OSD heartbeats on front from osd.412 [CON-161-A1,ContainerSquare,Risoe] to osd.706 [CON-161-A1,ContainerSquare,Risoe] 12913.173 msec After upgrade to octopus, this message now tries to be more helpful than before. Unfortunately, the one information that would really help is missing: the host bucket. Its the one piece I need, because its the hosts that have NICs. Is there any way to configure these messages such that they show the host bucket name? I have close to no way of finding these transceivers. They often don't show as TX/RX errors and also don't show in the switch log. Neither are the devices marked down by the OS. If I'm fast enough I can bring NIC ports down one by one and see what the slow ping goes away. But for this, I really need to be able to identify the offending host fast. It would be great if this message could be improved in this way. Thanks and best regards, ================= Frank Schilder AIT Risø Campus Bygning 109, rum S14 _______________________________________________ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io
