Jim Garlick writes:
 > Two more failures while running sanity in a loop overnight:
 > 
 >    - test 55 jbd assertion failure (i386 and x86_64)
 >        kernel: Assertion failure in journal_commit_transaction() at
 >        fs/jbd/commit.c:810: "jh->b_next_transaction == ((void *)0)"


This looks similar to:
https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=158363
. this seems reproductible without lustre patches (although less easily) 
. this has been discussed and corrected upstream (2.6.18 or 19).
. this may have been fixed with recent RHEL4U4 kernels (2.6.9.42.0.3.EL)

I just retested it with 2.6.12+relevant patches/lustre 1.4.6.1 (IA64)
and I do not observe it anymore with more than 1000 iterations.
(previously observed with 2.6.12/1.4.6beta with ~5-10 iterations).

-- 
[EMAIL PROTECTED]            | Tel: +33 (0)4 76 29 72 48
Bull SAS, Linux R&D, HPC/CI/Lustre     | Fax: +33 (0)4 76 61 52 52
1, Rue de Provence. BP208              | Office B1/386
38432 Echirolles Cedex, France         | Mail Stop B1/167


_______________________________________________
Lustre-discuss mailing list
[email protected]
https://mail.clusterfs.com/mailman/listinfo/lustre-discuss

Reply via email to