To follow-up on my own post. We apparently hit LU 2638/5626. I started a
dry-run fsck and see these fsck messages:
e2fsck 1.42.12.wc1 (15-Sep-2014)
Warning! /dev/mapper/vg_home-mdt is in use.
MMP interval is 10 seconds and total wait time is 42 seconds. Please wait...
Warning: skipping journal recovery because doing a read-only filesystem check.
Pass 1: Checking inodes, blocks, and sizes
HTREE directory inode 85863408 has an invalid root node.
Clear HTree index? no
...
Entry '..' in /ROOT/fas/miller/crs72 (85863408) is duplicate
'..' entry.
Fix? no
Entry '..' in /ROOT/fas/miller/crs72 (85863408) is duplicate '..' entry.
Fix? no
Problem in HTREE directory inode 85863408: block #0 has invalid limit (115)
Clear HTree index? no
Problem in HTREE directory inode 85863408: block #0 has invalid count (1571)
Clear HTree index? no
We are using e2fsprogs-1.42.12.wc1-7.el6.x86_64. If we run fsck, will it
"fix" the ".." directory entry errors ?
thanks,
chris hunter
On 10/27/2015 10:41 AM, Chris Hunter wrote:
Hi,
Our MDT volume went read-only this morning apparently due to a bad
directory entry:
> Oct 27 09:00:56 mds2 kernel: LDISKFS-fs error (device dm-10):
ldiskfs_dx_find_entry: bad entry in directory #85863408: rec_len % 4 !=
0 - block=42931201offset=24(24), inode=0, rec_len=2049, name_len=0
Does this indicate a problem with the MDT block device/hardware ?
We are using lustre 2.5.29.
thanks,
chris hunter
chris.hunter(a)yale.edu