On Sun, 6 Jan 2013, Drunkard Zhang wrote:
> Some times ago, I did ceph upgrade offline, then ethernet bonding
> while ceph online, and also I removed some OSDs, the cluster
> experienced big movements, after sometime it calms down finally. When
> I verify the consistance, I found that the filesystem size by 'ceph
> -s'(true size) and mounted size is different. What's the problem?
>
> It's still usable, and the used percent is right too, but the wrong
> size displayed looks really uncomfortable !!!
What OS and kernel are you running? In order to get big numbers to come
out of statfs, we report a huge block size, and some combinations of the
system utilies, glibc, or something else result in bad output. I don't
think we've ever fully tracked it down... :(
>
> log3 ~ # mount -t ceph log3:/ /mnt/temp/
> log3 ~ # df -t ceph
> Filesystem Size Used Avail Use% Mounted on
> 10.205.119.2:/ 404G 62G 343G 16% /mnt/temp
> log3 ~ # ceph -s
> health HEALTH_OK
> monmap e1: 3 mons at
> {log21=10.205.118.21:6789/0,log3=10.205.119.2:6789/0,squid86-log12=150.164.100.218:6789/0},
> election epoch 376, quorum 0,1,2 log21,log3,squid86-log12
> osdmap e15719: 37 osds: 37 up, 37 in
> pgmap v383025: 9224 pgs: 9224 active+clean; 7829 GB data, 15731 GB
> used, 87614 GB / 100 TB avail
> mdsmap e283: 1/1/1 up {0=log3=up:active}, 1 up:standby
> --
> To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
>
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
