Messages in this thread | | | Date | Tue, 24 May 2011 17:48:04 -0400 (EDT) | From | Vince Weaver <> | Subject | Re: perf: regression with PERF_EVENT_IOC_REFRESH |
| |
On Tue, 24 May 2011, Peter Zijlstra wrote:
> On Tue, 2011-05-24 at 17:11 +0200, Peter Zijlstra wrote: > > On Tue, 2011-05-24 at 11:04 -0400, Vince Weaver wrote: > > > As an aside, I also wasted 6 hours last night finding out that you don't > > > get signaled on overflow if you don't have a ring-buffer mmap()ed, even > > > if you never read from the buffer and you only are interested in counting > > > the number of overflows. > > > > That sounds like something we could fix, let me investigate. > > Does the below cure this? >
well that was an interesting interaction between debian-unstable and linus-git. Luckily a udev update seemed to help.
Anyway, your patch did not fix the problem. I still don't get overflow signals if the fd doesn't have a ring-buffer mmap()ed to it.
For a test case you can take my previous test case and comment out the mmap call. Since this test case is probably the only code in the world trying to do this, maybe it's not that important.
I can test further patches, but my fastest build machine here at home takes 3 hours to build a kernel so there will be some latency in the response.
Vince
| |