Messages in this thread | | | Date | Fri, 7 Mar 2008 10:02:57 +0100 | From | Ingo Molnar <> | Subject | Re: Linux 2.6.25-rc4 |
| |
* Jens Axboe <jens.axboe@oracle.com> wrote:
> > no luck - a few hundred successful randconfig bootups overnight > > (with a rather complex userspace startup to full X plus networking, > > and the testbox is used via the network to compile the next random > > kernel as well - etc.) and no failure at all. So there's not much we > > can do at this point - i'll keep you updated if anything new happens > > in the tests. > > OK, so it could possibly be something else or perhaps something that's > existed for a long time. > > To capture vital debugging information for cases like this, I had an > idea for a sysrq key that would dump queue and io scheduler info for > all known block devices. That should help pin point where the problem > lies. If we have any letters left in the sysrq namespace :-)
btw., we should reserve one sysrq letter as a "meta" character. If that letter is 'X' [for Xtended SysRq] then SysRq-X SysRq-B could dump the block info.
Ingo
| |