Description of problem: Seen on one of my HP ia64 Integrity servers running a proprietary HP test suite. Since all the messages are rather lengthy I wil upload it as an attachment. But here are some of what think are the more interesting messages: Slab corruption: (Not tainted) start=e0000040765c2828, len=104 kernel BUG at mm/slab.c:608! kjournald[541]: bugcheck! 0 [1] .... slab error in slab_destroy_objs(): cache `bio': start of a freed object was overwritten Version-Release number of selected component (if applicable): kernel-2.6.17-1.2364.fc6 How reproducible: This took about 10 hours of stress testing before it was seen. I will update this BZ if I see it again. Steps to Reproduce: 1. 2. 3. Actual results: Expected results: Additional info:
Created attachment 132317 [details] kernel messages from slab corruption runing the "busy2" test on hpdiablo1
We haven't seen this again, have we? Doug, any objections to closing this out? P.
I have not seen this in a while, yes I am OK with closing it.