Hi Sage, i would like to see the high ping problem fixed in 0.56.4 Thanks! Stefan Am 11.03.2013 um 23:56 schrieb Josh Durgin <josh.durgin@xxxxxxxxxxx>: > On 03/11/2013 08:02 AM, Wolfgang Hennerbichler wrote: >> also during writes. >> I've tested it now on linux with a virtio disk-drive: >> >> <disk type='network' device='disk'> >> <driver name='qemu' type='raw'/> >> <source protocol='rbd' name='rd/backup:rbd_cache=1'> >> <host name='rd-c2.ceph' port='6789'/> >> <host name='rd-c1.ceph' port='6789'/> >> <host name='wag-c1.ceph' port='6789'/> >> </source> >> <target dev='vda' bus='virtio'/> >> <address type='pci' domain='0x0000' bus='0x00' slot='0x06' >> function='0x0'/> >> </disk> >> >> virsh console to the running VM. >> Next - Write Test: >> dd if=/dev/zero of=/bigfile bs=2M & >> >> Serial console gets jerky, VM gets unresponsive. It doesn't crash, but >> it's not 'healthy' either. CPU load isn't very high, it's in the waiting >> state a lot: > > Does this only happen with rbd_cache turned on? If so, it may be the > same cause as http://tracker.ceph.com/issues/3737. > > Josh > >> Cpu(s): 0.0%us, 4.7%sy, 0.0%ni, 26.1%id, 68.4%wa, 0.0%hi, 0.3%si, >> 0.5%st >> 1170 root 20 0 11736 2452 556 D 8.5 0.5 0:00.80 dd >> >> >> Wolfgang >> >> On 03/11/2013 01:42 PM, Mark Nelson wrote: >>> I guess first question is does the jerky mouse behavior only happen >>> during reads or writes too? How is the CPU utilization in each case? >>> >>> Mark >>> >>> On 03/11/2013 01:30 AM, Wolfgang Hennerbichler wrote: >>>> Let me know if I can help out with testing somehow. >>>> >>>> Wolfgang >>>> ________________________________________ >>>> Von: ceph-users-bounces@xxxxxxxxxxxxxx >>>> [ceph-users-bounces@xxxxxxxxxxxxxx]" im Auftrag von "Mark >>>> Nelson [mark.nelson@xxxxxxxxxxx] >>>> Gesendet: Samstag, 09. März 2013 20:33 >>>> Bis: ceph-users@xxxxxxxxxxxxxx >>>> Betreff: Re: I/O Speed Comparisons >>>> >>>> Thanks for all of this feedback guys! It gives us some good data to try >>>> to replicate on our end. Hopefully I'll have some time next week to >>>> take a look. >>>> >>>> Thanks! >>>> Mark >>>> >>>> On 03/09/2013 08:14 AM, Erdem Agaoglu wrote: >>>>> Mark, >>>>> >>>>> If it's any help, we've done a small totally unreliable benchmark on our >>>>> end. For a KVM instance, we had: >>>>> 260MB/s write, 200MB/s read on local SAS disks, attached as LVM LVs, >>>>> 250MB/s write, 90MB/s read on RBD, 32 osds, all SATA. >>>>> >>>>> All sequential, a 10G network. It's more than enough currently but we'd >>>>> like to improve RBD read performance. >>>>> >>>>> Cheers, >>>>> >>>>> >>>>> On Sat, Mar 9, 2013 at 7:27 AM, Andrew Thrift <andrew@xxxxxxxxxxxxxxxxx >>>>> <mailto:andrew@xxxxxxxxxxxxxxxxx>> wrote: >>>>> >>>>> Mark, >>>>> >>>>> >>>>> I would just like to add, we too are seeing the same behavior with >>>>> QEMU/KVM/RBD. Maybe it is a common symptom of high IO with this >>>>> setup. >>>>> >>>>> >>>>> >>>>> Regards, >>>>> >>>>> >>>>> >>>>> >>>>> >>>>> Andrew >>>>> >>>>> >>>>> On 3/8/2013 12:46 AM, Mark Nelson wrote: >>>>> >>>>> On 03/07/2013 05:10 AM, Wolfgang Hennerbichler wrote: >>>>> >>>>> >>>>> >>>>> On 03/06/2013 02:31 PM, Mark Nelson wrote: >>>>> t >>>>> >>>>> If you are doing sequential reads, you may benefit by >>>>> increasing the >>>>> read_ahead_kb value for each device in >>>>> /sys/block/<device>/queue on the >>>>> OSD hosts. >>>>> >>>>> >>>>> Thanks, that didn't really help. It seems the VM has to >>>>> handle too much >>>>> I/O, even the mouse-cursor is jerking over the screen when >>>>> connecting >>>>> via vnc. I guess this is the wrong list, but it has somehow >>>>> to do with >>>>> librbd in connection with kvm, as the same machine on LVM >>>>> works just ok. >>>>> >>>>> >>>>> Thanks for the heads up Wolfgang. I'm going to be looking into >>>>> QEMU/KVM >>>>> RBD performance in the coming weeks so I'll try to watch out >>>>> for >>>>> this >>>>> behaviour. >>>>> >>>>> >>>>> Wolfgang > _______________________________________________ > ceph-users mailing list > ceph-users@xxxxxxxxxxxxxx > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |