Messages in this thread | | | Date | Mon, 8 Jul 2013 22:56:38 +0200 | Subject | Re: [PATCH] perf: fix interrupt handler timing harness | From | Stephane Eranian <> |
| |
On Mon, Jul 8, 2013 at 10:54 PM, Andi Kleen <ak@linux.jf.intel.com> wrote: >> I did a quite a bit of ftracing to look for spots inside the handler >> which were taking large amounts of time. There were none. The >> execution time was spread very evenly over the entire nmi handler. It >> didn't appear to be any individual hot cachelines or doing something >> silly like sitting in a loop handling lots of PMU events. > > In some cases callgraphs seemed to be quite expensive (large fraction > of the handler time) > In my case, I am not doing callgraphs, just regular cycles.
| |