Hello,

I have an interesting situation one of our lustre file systems where I cannot rename files or directories across a specific directory boundary but I can create hard links across the same boundary. The relevant section of strace for 'mv' follows:

=====
geteuid()                               = 0
ioctl(0, TCGETS, {B38400 opost isig icanon echo ...}) = 0
stat("..", {st_mode=S_IFDIR|0755, st_size=11776, ...}) = 0
lstat("test.txt", {st_mode=S_IFREG|0644, st_size=765876794, ...}) = 0
lstat("../test.txt", 0x7fff36c3ff30) = -1 ENOENT (No such file or directory) renameat2(AT_FDCWD, "test.txt", AT_FDCWD, "../test.txt", 0) = -1 EXDEV (Invalid cross-device link)
=====

The systems I've tested this on are in our nosquash_nids list as they were used for cluster array jobs to copy data between a retiring file system and a new one. The clients are either 2.10 or 2.12. The file system is run by 2.12.2 on zfs.

nodemap is not active.

Best,
Jesse Stroik

Attachment: smime.p7s
Description: S/MIME Cryptographic Signature

_______________________________________________
lustre-discuss mailing list
lustre-discuss@lists.lustre.org
http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org

Reply via email to