Note: the following does not currently work in Firefly because of http://tracker.ceph.com/issues/9677 . It has been backported to Firefly and will likely be in 0.80.8.
The disk I/O of a Ceph OSD thread scrubbing is the same as all other threads by default. It can be lowered with ioprio options for all OSDs with:
ceph tell osd.* injectargs '--osd_disk_thread_ioprio_priority 7' ceph tell osd.* injectargs '--osd_disk_thread_ioprio_class idle'
All other threads in the OSD will be be (best effort) with priority 4 which is the default for daemons. The disk thread will show as idle:
$ sudo iotop --batch --iter 1 | grep 'ceph-osd -i 0' | grep -v be/4 4156 idle loic 0.00 B/s 0.00 B/s 0.00 % 0.00 % ./ceph-osd -i 0 ..
The change will only be effective if the scheduler is cfq (it can safely be modified at runtime)
# cat /sys/block/sda/queue/scheduler noop [deadline] cfq # echo cfq > /sys/block/sda/queue/scheduler
To display the current value for a given OSD the following can be run from the host on which it is running (because it uses the asok file found in /var/run/ceph):
$ ceph daemon osd.0 config get osd_disk_thread_ioprio_class { "osd_disk_thread_ioprio_class": "idle"} $ ceph daemon osd.0 config get osd_disk_thread_ioprio_priority { "osd_disk_thread_ioprio_priority": "7"}
Is the change permanent? If not, how can me make it so?
I’ve difficulties checking the current state on my servers, for example on the server runing osd.0 :
# ceph daemon osd.0 config get osd_disk_thread_ioprio_class
{ “error”: “error getting ‘osd_disk_thread_ioprio_class’: (2) No such file or directory”}
/var/run/ceph/ceph-osd.0.asock exists, this is 0.80.5 on Gentoo Linux packaged by the distribution.
It was added in 0.80.6 http://ceph.com/releases/v0-80-6-firefly-released/ : osd: introduce optional sleep, io priority for scrub and snap trim (Sage Weil)
The change can be made permanent by adding osd_disk_thread_ioprio_class and osd_disk_thread_ioprio_priority in ceph.conf