I'm sending this out before I have complete information, thinking somebody may
recognize the problem and cut me off.
CentOS 5, tested on kernels 2.6.18-53.1.21.el5 and 2.6.18-53.1.13.el5 (patched
for lustre, testing originals now).
Kernel panic while "accessing lots of files." E.g., du -s * on a large volume.
Happens with memcache or disk cache
I need to capture a complete stack trace, but wrote this partial one down last
night:
do_lookup
__link_path_walk
generic_file_llseek
current_fs_time
:openafs:afs_access
__mark_inode_dirty
do_path_lookup
getname
__user_walk_fd
vfs_lstat_fd
crash was in afs_FlushVCache
I'll collect something more complete info soon. Seems to be easily reproducible.
--
// Miles Davis - [EMAIL PROTECTED] - http://www.cs.stanford.edu/~miles
// Computer Science Department - Computer Facilities
// Stanford University
_______________________________________________
OpenAFS-info mailing list
[email protected]
https://lists.openafs.org/mailman/listinfo/openafs-info
