On Wed, Sep 23, 2020 at 05:05:30PM +0900, Namhyung Kim wrote: > Hello, > > This is my second attempt to speed up build-id injection. As this is > to improve performance, I've added a benchmark for it. Please look at > the usage in the first commit. > > By default, it measures average processing time of 100 MMAP2 events > and 10000 SAMPLE events. Below is the current result on my laptop. > > $ perf bench internals inject-build-id > # Running 'internals/inject-build-id' benchmark: > Average build-id injection took: 22.997 msec (+- 0.067 msec) > Average time per event: 2.255 usec (+- 0.007 usec) > > With this patchset applied, it got this: > > $ perf bench internals inject-build-id > # Running 'internals/inject-build-id' benchmark: > Average build-id injection took: 18.441 msec (+- 0.106 msec) > Average time per event: 1.808 usec (+- 0.010 usec) > Average build-id-all injection took: 13.451 msec (+- 0.132 msec) > Average time per event: 1.319 usec (+- 0.013 usec)
nice, I can see that speed up as well Acked-by: Jiri Olsa <[email protected]> thanks, jirka
