Hi, On 06/18/2015 12:54 PM, Alexandre DERUMIER wrote:
Hi, for read benchmark with fio, what is the iodepth ? my fio 4k randr results with iodepth=1 : bw=6795.1KB/s, iops=1698 iodepth=2 : bw=14608KB/s, iops=3652 iodepth=4 : bw=32686KB/s, iops=8171 iodepth=8 : bw=76175KB/s, iops=19043 iodepth=16 :bw=173651KB/s, iops=43412 iodepth=32 :bw=336719KB/s, iops=84179
I'm trying multiple versions - from one job and iodepth=1 to 16 jobs with iodepth 32, similar to what You do.
I'm less worried about the bandwidth now, since I found out about the Intel SSD 530 problem (the dsync stuff).
I'm worried about iops - when I test it locally I get the expected ~40k iops on a ssd drive, but when I do it from a client I get 2-4k iops..
(This should be similar with rados bench -t (threads) option). This is normal because of network latencies + ceph latencies. Doing more parallism increase iops.
yes, I'm expecting that, but for now I can't get close to what I should see using SSD as an OSD in ceph..
(doing a bench with "dd" = iodepth=1)
I'm only using dd to test seq read/write speed.
Theses result are with 1 client/rbd volume. now with more fio client (numjobs=X) I can reach up to 300kiops with 8-10 clients.
I would love to see these results in my setup :) J _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com