The disk performance baseline test will be done in two steps. First, we will measure the performance of a single disk, and after that, we will measure the performance of all the disks connected to one Ceph OSD node simultaneously.
Note
To get realistic results, I am running the benchmarking tests described in this recipe against a Ceph cluster deployed on physical hardware. We can also run these tests on the Ceph cluster, hosted on virtual machine, but we might not get appealing results.
To get the disk read and write performance, we will use the dd
command with oflag
set to direct
in order to bypass disk cache for realistic results.
Drop caches:
# echo 3 > /proc/sys/vm/drop_caches
Use
dd
to write a file nameddeleteme
of the size10G
, filled with zeros/dev/zero
as the input fileif
to the directory where Ceph OSD is mounted, that is,/var/lib/ceph/osd/ceph-0/
.# dd if=/dev/zero of=/var/lib/ceph/osd/ceph-0/deleteme bs...