Messages in this thread | | | Date | Thu, 26 Mar 2009 13:22:27 +1100 | From | Paul Mackerras <> | Subject | Re: [PATCH 5/6] perf_counter: kerneltop: mmap_pages argument |
| |
Peter Zijlstra writes:
> One possible solution is making the control page writable and writing > the userspace read position to it, then the kernel can, on > perf_output_begin() detect the overflow and count the number of > overwritten events. > > This overflow count could then be published back into the control page.
We could in principle have many different processes mmapping the same counter and reading the ring buffer, couldn't we? So which process gets to put its read position in the control page?
> TBH I'm not much of a fan, making all these pages writable just opens a > whole can of worms, and that accurate overflow tracking will put more > code in the output path.
I agree.
Paul.
| |