[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <f31785d9-b12d-4826-d790-b41686135280@linux.intel.com>
Date: Mon, 5 Mar 2018 09:28:27 -0500
From: "Liang, Kan" <kan.liang@...ux.intel.com>
To: Jiri Olsa <jolsa@...hat.com>
Cc: acme@...nel.org, mingo@...hat.com, linux-kernel@...r.kernel.org,
namhyung@...nel.org, wangnan0@...wei.com, ak@...ux.intel.com
Subject: Re: [PATCH 02/14] perf trace: Apply new perf_mmap__read_event()
interface
On 3/2/2018 6:30 PM, Jiri Olsa wrote:
> On Thu, Mar 01, 2018 at 06:08:59PM -0500, kan.liang@...ux.intel.com wrote:
>> From: Kan Liang <kan.liang@...ux.intel.com>
>>
>> The perf trace still use the legacy interface.
>>
>> Apply the new perf_mmap__read_event() interface for perf trace.
>>
>> No functional change.
>>
>> Signed-off-by: Kan Liang <kan.liang@...ux.intel.com>
>> ---
>> tools/perf/builtin-trace.c | 11 +++++++++--
>> 1 file changed, 9 insertions(+), 2 deletions(-)
>>
>> diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
>> index e7f1b18..a46644f 100644
>> --- a/tools/perf/builtin-trace.c
>> +++ b/tools/perf/builtin-trace.c
>> @@ -2472,8 +2472,14 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
>>
>> for (i = 0; i < evlist->nr_mmaps; i++) {
>> union perf_event *event;
>> + struct perf_mmap *md;
>> + u64 end, start;
>>
>> - while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
>> + md = &evlist->mmap[i];
>> + if (perf_mmap__read_init(md, 0, &start, &end) < 0)
>> + continue;
>
> should we break the loop if this returns -EINVAL?
>
It only means the ring buffer is broken for current mmaps.
For others, the data should still be good.
I don't think we should drop them by breaking the loop.
Also, the -EINVAL is only valid for overwrite mode. It is impossible to
return -EINVAL in current code.
Thanks,
Kan
> jirka
>
>> +
>> + while ((event = perf_mmap__read_event(md, 0, &start, end)) != NULL) {
>> struct perf_sample sample;
>>
>> ++trace->nr_events;
>> @@ -2486,7 +2492,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
>>
>> trace__handle_event(trace, event, &sample);
>> next_event:
>> - perf_evlist__mmap_consume(evlist, i);
>> + perf_mmap__consume(md, 0);
>>
>> if (interrupted)
>> goto out_disable;
>> @@ -2496,6 +2502,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
>> draining = true;
>> }
>> }
>> + perf_mmap__read_done(md);
>> }
>>
>> if (trace->nr_events == before) {
>> --
>> 2.4.11
>>
Powered by blists - more mailing lists