Messages in this thread | | | Date | Tue, 18 Aug 2009 16:00:22 +0200 | From | Ingo Molnar <> | Subject | Re: [PATCH] perf_counter: Fix a race on perf_counter_ctx |
| |
* Metzger, Markus T <markus.t.metzger@intel.com> wrote:
> Well, that would push out the limit a bit, but it would still be > quite fragile. > > Currently, I'm not sure that this (i.e. that the interrupt > handling takes too long) is the underlying problem of the hangs > that I'm seeing.
I havent seen a plausible theory yet about why an actual lockup would happen on your box.
Does the timer IRQ perhaps slow down to such a degree that it can never make progress and gets re-triggered again and again? We saw such things with the function tracer.
Did the sampling of kernel-mode tasks ever work with the old BTS code?
Ingo
| |