2012/12/19 Sage Weil <sage@xxxxxxxxxxx>: > On Wed, 19 Dec 2012, Mark Kirkwood wrote: >> On 19/12/12 15:56, Drunkard Zhang wrote: >> > 2012/12/19 Mark Kirkwood <mark.kirkwood@xxxxxxxxxxxxxxx>: >> > > On 19/12/12 14:44, Drunkard Zhang wrote: >> > > > 2012/12/16 Drunkard Zhang <gongfan193@xxxxxxxxx>: >> > > > > I couldn't rm files in ceph, which was backuped files of one osd. It >> > > > > reports direcory not empty, but there's nothing under that directory, >> > > > > just the directory itself held some spaces. How could I shoot down the >> > > > > problem ? >> > > > > >> > > > > log30 /mnt/bc # ls -aR osd.28/ >> > > > > osd.28/: >> > > > > . .. osd.28 >> > > > > >> > > > > osd.28/osd.28: >> > > > > . .. current >> > > > > >> > > > > osd.28/osd.28/current: >> > > > > . .. 0.537_head >> > > > > >> > > > > osd.28/osd.28/current/0.537_head: >> > > > > . .. >> > > > > log30 /mnt/bc # ls -lhd osd.28/osd.28/current/0.537_head >> > > > > drwxr-xr-x 1 root root 119M Dec 14 19:22 >> > > > > osd.28/osd.28/current/0.537_head >> > > > > log30 /mnt/bc # >> > > > > log30 /mnt/bc # rm -rf osd.28/ >> > > > > rm: cannot remove ?osd.28/osd.28/current/0.537_head?: Directory not >> > > > > empty >> > > > > log30 /mnt/bc # rm -rf osd.28/osd.28/current/0.537_head >> > > > > rm: cannot remove ?osd.28/osd.28/current/0.537_head?: Directory not >> > > > > empty >> > > > > >> > > > > The cluster seems health: >> > > > > 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 640, quorum 0,1,2 log21,log3,squid86-log12 >> > > > > osdmap e1864: 45 osds: 45 up, 45 in >> > > > > pgmap v163907: 9224 pgs: 9224 active+clean; 3168 GB data, 9565 >> > > > > GB >> > > > > used, 111 TB / 120 TB avail >> > > > > mdsmap e134: 1/1/1 up {0=log14=up:active}, 1 up:standby >> > > > > >> > > > After mds restart, I got this error message: >> > > > 2012-12-19 09:16:24.837045 mds.0 [ERR] unmatched fragstat size on >> > > > single dirfrag 100000006c7, inode has f(v6 m2012-11-24 23:18:34.947266 >> > > > 1773=1773+0), dirfrag has f(v6 m2012-12-17 12:43:52.203358 >> > > > 2038=2038+0) >> > > > >> > > > How can I fix this? >> > > > >> > > Is it a btrfs filesystem? If so will have sub volumes hiding in there you >> > > need to remove 1st. >> > Thanks for reply, osds all lives on xfs filesystem. >> >> Ah, right - might be worth showing us output of 'ls -la' in the dir concerned. >> In particular the link counts might be wrong (indicating fs corruption, >> probably fixable with xfs_repair). > Sorry for late response, but I was involved in another stuck problem, turns out it's firewall rules lost :( Here's ls of this directory recursively: log1 /mnt/bc # ls -laR osd.28/ osd.28/: total 0 drwxr-xr-x 1 root root 124379978 Dec 13 23:04 . drwxr-xr-x 1 root root 7251593161780 Dec 19 01:05 .. drwxr-xr-x 1 root root 124379978 Dec 14 19:24 osd.28 osd.28/osd.28: total 0 drwxr-xr-x 1 root root 124379978 Dec 14 19:24 . drwxr-xr-x 1 root root 124379978 Dec 13 23:04 .. drwxr-xr-x 1 root root 124379978 Dec 14 19:24 current osd.28/osd.28/current: total 0 drwxr-xr-x 1 root root 124379978 Dec 14 19:24 . drwxr-xr-x 1 root root 124379978 Dec 14 19:24 .. drwxr-xr-x 1 root root 124379978 Dec 16 12:40 0.537_head osd.28/osd.28/current/0.537_head: total 0 drwxr-xr-x 1 root root 124379978 Dec 16 12:40 . drwxr-xr-x 1 root root 124379978 Dec 14 19:24 .. log1 /mnt/bc # > This is a problem in the MDS, not the fs underneath the OSDs. There was > at least one bug that was corrupting the 'rstats' recursive info that > could lead to this that has been fixed recently. > > The MDS is actually repairing this as it goes, unless you specify the 'mds > verify scatter = true' option, in which case it will assert and kill > itself. > So, I can fix this problem by set this option? 'mds verify scatter = true' -- 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