Messages in this thread | | | Date | Wed, 22 Jun 2022 12:39:00 -0400 | From | "Shawn M. Chapla" <> | Subject | Re: [PATCH] perf data: Prefer sampled CPU when exporting JSON |
| |
On Wed, Jun 22, 2022 at 01:30:30PM -0300, Arnaldo Carvalho de Melo wrote: > Em Wed, Jun 22, 2022 at 10:42:43AM -0400, Shawn M. Chapla escreveu: > > On Thu, May 26, 2022 at 04:14:47PM -0400, Shawn M. Chapla wrote: > > > When CPU has been explicitly sampled (via --sample-cpu), prefer this > > > sampled value over the thread CPU value when exporting to JSON. > > > > Signed-off-by: Shawn M. Chapla <schapla@codeweavers.com> > > > --- > > > tools/perf/util/data-convert-json.c | 5 ++++- > > > 1 file changed, 4 insertions(+), 1 deletion(-) > > > > > > diff --git a/tools/perf/util/data-convert-json.c b/tools/perf/util/data-convert-json.c > > > index f1ab6edba446..613d6ae82663 100644 > > > --- a/tools/perf/util/data-convert-json.c > > > +++ b/tools/perf/util/data-convert-json.c > > > @@ -149,6 +149,7 @@ static int process_sample_event(struct perf_tool *tool, > > > struct convert_json *c = container_of(tool, struct convert_json, tool); > > > FILE *out = c->out; > > > struct addr_location al, tal; > > > + u64 sample_type = __evlist__combined_sample_type(evsel->evlist); > > > u8 cpumode = PERF_RECORD_MISC_USER; > > > > > > if (machine__resolve(machine, &al, sample) < 0) { > > > @@ -168,7 +169,9 @@ static int process_sample_event(struct perf_tool *tool, > > > output_json_key_format(out, true, 3, "pid", "%i", al.thread->pid_); > > > output_json_key_format(out, true, 3, "tid", "%i", al.thread->tid); > > > > > > - if (al.thread->cpu >= 0) > > > + if ((sample_type & PERF_SAMPLE_CPU)) > > > + output_json_key_format(out, true, 3, "cpu", "%i", sample->cpu); > > > + else if (al.thread->cpu >= 0) > > > output_json_key_format(out, true, 3, "cpu", "%i", al.thread->cpu); > > > > > > output_json_key_string(out, true, 3, "comm", thread__comm_str(al.thread)); > > > -- > > > 2.36.1 > > > > > > > Just checking in to see if anyone has had a chance to take a look at > > this yet. > > Seems sensible, applying to perf/core for 5.20. > > - Arnaldo
Thank you! I appreciate it.
Cheers, Shawn
| |