[LU-5089] LustreError: 10147:0:(file.c:3073:ll_inode_revalidate_fini()) tickfs: revalidate FID [0x200000007:0x1:0x0] error: rc = -13 Created: 19/May/14  Updated: 21/May/14  Resolved: 19/May/14

Status: Resolved
Project: Lustre
Component/s: None
Affects Version/s: Lustre 2.5.1
Fix Version/s: None

Type: Bug Priority: Major
Reporter: James A Simmons Assignee: WC Triage
Resolution: Not a Bug Votes: 0
Labels: None
Environment:

SLES11 SP1 or SP3 clients. Using latest lustre 2.5.1 server back end on RHEL6.5 and lustre 2.5.1 clients.


Severity: 3
Rank (Obsolete): 14026

 Description   

With a newly created file system I'm seeing the following errors on my clients.

LustreError: 10147:0:(mdc_locks.c:916:mdc_enqueue()) ldlm_cli_enqueue: -13
LustreError: 10147:0:(mdc_locks.c:916:mdc_enqueue()) Skipped 1979 previous similar messages
LustreError: 10147:0:(file.c:3073:ll_inode_revalidate_fini()) tickfs: revalidate FID [0x200000007:0x1:0x0] error: rc = -13
LustreError: 10147:0:(file.c:3073:ll_inode_revalidate_fini()) Skipped 1979 previous similar messages
LustreError: 10147:0:(mdc_locks.c:916:mdc_enqueue()) ldlm_cli_enqueue: -13

When I attempt as a user to use the file system I'm denied and with ls I see

ls -al
ls: cannot access tick: Permission denied
total 28
drwxr-xr-x 8 root root 4096 May 19 14:40 .
drwxr-xr-x 32 root root 4096 Jan 15 21:01 ..
drwxr-xr-x 2 root root 4096 May 19 2011 barry
drwxr-xr-x 2 root root 4096 Aug 18 2013 fiyona
drwxr-xr-x 2 root root 4096 Oct 3 2013 robinhoodfs
drwxr-xr-x 2 root root 4096 Jan 17 02:32 sultan
d????????? ? ? ? ? ? tick
drwxr-xr-x 2 root root 4096 Jan 26 2011 yonafs

As you can see tick is my mount point and it hosed. I don't see any errors on the server side. Only the client side.



 Comments   
Comment by Bob Glossman (Inactive) [ 19/May/14 ]

James, Are you sure you have matching UIDs on SLES clients & RHEL servers? Default UID ranges for ordinary users aren't the same in these two distros. Without taking care to make them match horrible access problems can happen. I've been bitten that way frequently.

Comment by James A Simmons [ 19/May/14 ]

we use ldap eveywhere? Also the results are not consistent. Sometimes I can read a directory then other times I can.

Comment by James A Simmons [ 19/May/14 ]

I found it was our ldap server is currently not working on my MDS. Sorry for the noise but you can close the ticket.

Comment by John Fuchs-Chesney (Inactive) [ 19/May/14 ]

Thanks James.
~ jfc.

Comment by James A Simmons [ 19/May/14 ]

One small comment. Perhaps we can write this up some where so when people see this error they know what the source of the problem is.

Comment by Peter Jones [ 21/May/14 ]

Where do you think would be suitable James? Is this something to include in the manual?

Generated at Sat Feb 10 01:48:26 UTC 2024 using Jira 9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c.