2013/1/6 Drunkard Zhang <gongfan193@xxxxxxxxx>: > 2013/1/6 Sage Weil <sage@xxxxxxxxxxx>: >> 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... :( >> > All nodes are based on Gentoo, and up-to-date. > > # emerge --info > Portage 2.1.11.31 (default/linux/amd64/10.0, gcc-4.6.3, glibc-2.15-r3, > 3.7.1-gentoo x86_64) > ================================================================= > System uname: Linux-3.7.1-gentoo-x86_64-Intel-R-_Xeon-R-_CPU_E5620_@_2.40GHz-with-gentoo-2.1 Sorry, I lost the ceph version, it's ceph-0.55.1. -- 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
