User Story: As an admin, I want to see which RBD clients by IP address are generating the most IOPS so I can spot noisy hosts on my client network. As an admin, I want to see which RBD clients by Virtual Machine on a hypervisor are generating the most IOPS so I can spot noisy neighbors in an OpenStack environment Notes: It is expected that that this will be implemented on top of ceph-mgr.
Updating the QA Contact to a Hemant. Hemant will be rerouting them to the appropriate QE Associate. Regards, Giri
Verified the bug on latest ceph version and the feature is working as expected. rbd: waiting for initial image stats NAME WR RD WR_BYTES RD_BYTES WR_LAT RD_LAT librbd 24/s 0/s 36 MiB/s 0 B/s 171.57 ms 0.00 ns NAME WR RD WR_BYTES RD_BYTES WR_LAT RD_LAT librbd 34/s 0/s 56 MiB/s 0 B/s 184.74 ms 0.00 ns NAME WR RD WR_BYTES RD_BYTES WR_LAT RD_LAT librbd 0/s 160/s 252 KiB/s 4.8 MiB/s 24.78 ms 1.42 ms NAME WR RD WR_BYTES RD_BYTES WR_LAT RD_LAT librbd 0/s 218/s 306 KiB/s 3.2 MiB/s 31.53 ms 785.37 us NAME WR RD WR_BYTES RD_BYTES WR_LAT RD_LAT librbd 2/s 311/s 4.3 MiB/s 3.1 MiB/s 114.77 ms 518.63 us NAME WR RD WR_BYTES RD_BYTES WR_LAT RD_LAT librbd 56/s 47/s 33 MiB/s 2.5 MiB/s 232.68 ms 4.82 ms ceph version 14.2.4-91.el8cp (23607558df3b077b6190cdf96cd8d9043aa2a1c5) nautilus (stable) ceph-mon-14.2.4-91.el8cp.x86_64 ansible-2.8.7-1.el8ae.noarch ceph-ansible-4.0.6-1.el8cp.noarch
Since the problem described in this bug report should be resolved in a recent advisory, it has been closed with a resolution of ERRATA. For information on the advisory, and where to find the updated files, follow the link below. If the solution does not work for you, open a new bug report. https://access.redhat.com/errata/RHBA-2020:0312