Messages in this thread | | | Date | Thu, 28 May 2015 14:06:51 +0200 | From | Peter Zijlstra <> | Subject | Re: sched_setscheduler() vs idle_balance() race |
| |
On Thu, May 28, 2015 at 02:04:21PM +0200, Mike Galbraith wrote: > On Thu, 2015-05-28 at 13:51 +0200, Peter Zijlstra wrote:
> > Which is exactly the hole you mean, right? > > Yeah, but that hole is way older than dl. Box falling into it is > running SLE11, which is.. well, still somewhat resembles 3.0.
Oh sure, that patch just recognised there was a hole there and put a comment in. We further failed to spot the fail you just did.
Right mess though, I think I already found some of those 'obvious' reasons mentioned in the previous email.
| |