Messages in this thread | | | Date | Fri, 12 Dec 2014 07:54:11 +0100 | From | Ingo Molnar <> | Subject | Re: frequent lockups in 3.18rc4 |
| |
* Sasha Levin <sasha.levin@oracle.com> wrote:
> Right, and it reproduces in 3.10 as well, so it's not really a > new thing. > > What's odd is that I don't remember seeing this bug so long in > the past, I'll try bisecting trinity rather than the kernel - > it's the only other thing that changed.
So I think DaveJ mentioned it that Trinity recently changed its test task count and is now more aggressively loading the system. Such a change might have made a dormant, resource limits related bug or load dependent race more likely.
I think at this point it would also be useful to debug the hang itself directly: using triggered printks and kgdb and drilling into all the data structures to figure out why the system isn't progressing.
If the bug triggers in a VM (which your testing uses) the failed kernel state ought to be a lot more accessible than bare metal.
That it triggers in a VM, and if it's the same bug as DaveJ's, that also makes the hardware bug theory a lot less likely.
Thanks,
Ingo
| |