setup a bitter value for read_ahead_kb ? I tested with 256 MB read ahead cache (
From: ceph-users-bounces@xxxxxxxxxxxxxx [mailto:ceph-users-bounces@xxxxxxxxxxxxxx] On Behalf Of ???? ???????
Sent: Friday, February 07, 2014 10:55 AM
To: Konrad Gutkowski
Cc: ceph-users@xxxxxxxxxxxxxx
Subject: Re: RBD+KVM problems with sequential read
echo "noop">/sys/block/vda/queue/scheduler
echo "1000" >/sys/block/vda/queue/nr_requests
echo "8192">/sys/block/vda/queue/read_ahead_kb
[root@nfs tmp]# dd if=test of=/dev/null
39062500+0 records in
39062500+0 records out
20000000000 bytes (20 GB) copied, 244.024 s, 82.0 MB/s
Changing these parameters are not affected...
Are there other ideas on this problem?
Thank you.
2014-02-07 Konrad Gutkowski <konrad.gutkowski@xxxxxx>:
Hi,
W dniu 07.02.2014 o 08:14 Ирек Фасихов <malmyzh@xxxxxxxxx> pisze:
[...]
Why might such a low speed sequential read? Do ideas on this issue?
Iirc you need to set your readahead for the device higher (inside the vm) to compensate for network rtt.
blockdev --setra x /dev/vda
Thanks.
--
С уважением, Фасихов Ирек Нургаязович
Моб.: +79229045757
Regards,
Konrad Gutkowski
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
--
С уважением, Фасихов Ирек Нургаязович
Моб.: +79229045757
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
