| Thank you Greg, thank you Kenneth,
i have enabled ntp now and the clock skew is getting smaller and it’s gone after a while, so everything is fine now. I already thought the virtual Disks could slow down things, now i know it for sure. My last question (for now): Is there any difference between rbd’s and a mounted cephFS concerning of the performance?
Thank you in advance, Florian
On 3/12/2014 6:24 PM, Florian Krauß
wrote:
Hello everyone,
this is the first time i ever write to a mailing list, please be patient with me (especially for my poor english)…
Im trying to reach my Bachelors Degree in Computer Science, Im doing a Project which involves ceph.
I’am able to setup a ceph Cluster, but there are a few things i can’t Figure out…
As I’am setting up the cluster with virtual machines im facing a little Problem:
clock skew: every time i reboot on node a clock skew is detected. If i restart the Monitor on which the clock skew is detected the Problem is gone. But this is not what i want to show in my presentation. I already enabled the VMware tools, but the Problem persists. Does it make more sense to enable NTP?
You'll most likely need to setup NTP. I don't know of any better way
to sync clocks so be sure to install NTP on ceph nodes. You should
setup a local NTP server on your lan so that latency is very small
Are there any performance Issues to expect if i use a drive with ceph-disk-prepare (or activate) /dev/sdb directly ?
Are there any (big) performance Issues to expect using these virtual drives instead of „real“ drives?
Yes, virtual machine hard drives can be slower than hardware drives
so performance may be slower.
Kind regards
Florian
_______________________________________________
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
|
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
