lkml.org 
[lkml]   [2021]   [Feb]   [18]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [PATCH] perf record: Fix continue profiling after draining the buffer
From
Date
Hello,

On 2021/2/7 8:56, Yang Jihong wrote:
> Hello,
>
> On 2021/2/5 18:46, Jiri Olsa wrote:
>> On Fri, Feb 05, 2021 at 07:35:22PM +0900, Namhyung Kim wrote:
>>> Hello,
>>>
>>> On Fri, Feb 5, 2021 at 3:50 PM Yang Jihong <yangjihong1@huawei.com>
>>> wrote:
>>>>
>>>> commit da231338ec9c098707c8a1e4d8a50e2400e2fe17 uses eventfd to
>>>> solve rare race
>>>> where the setting and checking of 'done' which add done_fd to pollfd.
>>>> When draining buffer, revents of done_fd is 0 and evlist__filter_pollfd
>>>> function returns a non-zero value.
>>>> As a result, perf record does not stop profiling.
>>>>
>>>> The following simple scenarios can trigger this condition:
>>>>
>>>> sleep 10 &
>>>> perf record -p $!
>>>>
>>>> After the sleep process exits, perf record should stop profiling and
>>>> exit.
>>>> However, perf record keeps running.
>>>>
>>>> If pollfd revents contains only POLLERR or POLLHUP,
>>>> perf record indicates that buffer is draining and need to stop
>>>> profiling.
>>>> Use fdarray_flag__nonfilterable to set done eventfd to nonfilterable
>>>> objects,
>>>> so that evlist__filter_pollfd does not filter and check done eventfd.
>>>>
>>>> Fixes: da231338ec9c (perf record: Use an eventfd to wakeup when done)
>>>> Signed-off-by: Yang Jihong <yangjihong1@huawei.com>
>>>> ---
>>>>   tools/perf/builtin-record.c | 2 +-
>>>>   tools/perf/util/evlist.c    | 8 ++++++++
>>>>   tools/perf/util/evlist.h    | 4 ++++
>>>>   3 files changed, 13 insertions(+), 1 deletion(-)
>>>>
>>>> diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
>>>> index fd3911650612..51e593e896ea 100644
>>>> --- a/tools/perf/builtin-record.c
>>>> +++ b/tools/perf/builtin-record.c
>>>> @@ -1663,7 +1663,7 @@ static int __cmd_record(struct record *rec,
>>>> int argc, const char **argv)
>>>>                  status = -1;
>>>>                  goto out_delete_session;
>>>>          }
>>>> -       err = evlist__add_pollfd(rec->evlist, done_fd);
>>>> +       err = evlist__add_wakeup_eventfd(rec->evlist, done_fd);
>>>>          if (err < 0) {
>>>>                  pr_err("Failed to add wakeup eventfd to poll list\n");
>>>>                  status = err;
>>>> diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
>>>> index 05363a7247c4..fea4c1e8010d 100644
>>>> --- a/tools/perf/util/evlist.c
>>>> +++ b/tools/perf/util/evlist.c
>>>> @@ -572,6 +572,14 @@ int evlist__filter_pollfd(struct evlist
>>>> *evlist, short revents_and_mask)
>>>>          return perf_evlist__filter_pollfd(&evlist->core,
>>>> revents_and_mask);
>>>>   }
>>>>
>>>> +#ifdef HAVE_EVENTFD_SUPPORT
>>>> +int evlist__add_wakeup_eventfd(struct evlist *evlist, int fd)
>>>> +{
>>>> +       return perf_evlist__add_pollfd(&evlist->core, fd, NULL, POLLIN,
>>>> +                                      fdarray_flag__nonfilterable);
>>>> +}
>>>> +#endif
>>>
>>> Does it build when HAVE_EVENTFD_SUPPORT is not defined?
>>
>> yea, I was wondering the same.. but it's called only from
>> code within HAVE_EVENTFD_SUPPORT ifdef
>>
>> jirka
>>
>>>
>>> Thanks,
>>> Namhyung
>>>
>>>
> I have tested that if "eventfd" feature is removed from the
> FEATURE_TESTS_BASIC list in Makefile.feature,
> evlist__add_wakeup_eventfd will not be build.
>
> Modify as follows:
>
> diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
> index 97cbfb31b762..d1603050764a 100644
> --- a/tools/build/Makefile.feature
> +++ b/tools/build/Makefile.feature
> @@ -32,7 +32,6 @@ FEATURE_TESTS_BASIC :=                  \
>          backtrace                       \
>          dwarf                           \
>          dwarf_getlocations              \
> -        eventfd                         \
>          fortify-source                  \
>          sync-compare-and-swap           \
>          get_current_dir_name            \
>
> Thanks,
> Yang
>
>>>> +
>>>>   int evlist__poll(struct evlist *evlist, int timeout)
>>>>   {
>>>>          return perf_evlist__poll(&evlist->core, timeout);
>>>> diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
>>>> index 1aae75895dea..6d4d62151bc8 100644
>>>> --- a/tools/perf/util/evlist.h
>>>> +++ b/tools/perf/util/evlist.h
>>>> @@ -142,6 +142,10 @@ struct evsel
>>>> *evlist__find_tracepoint_by_name(struct evlist *evlist, const char
>>>>   int evlist__add_pollfd(struct evlist *evlist, int fd);
>>>>   int evlist__filter_pollfd(struct evlist *evlist, short
>>>> revents_and_mask);
>>>>
>>>> +#ifdef HAVE_EVENTFD_SUPPORT
>>>> +int evlist__add_wakeup_eventfd(struct evlist *evlist, int fd);
>>>> +#endif
>>>> +
>>>>   int evlist__poll(struct evlist *evlist, int timeout);
>>>>
>>>>   struct evsel *evlist__id2evsel(struct evlist *evlist, u64 id);
>>>> --
>>>> 2.17.1
>>>>
>>>
>>
>> .
>>
Do have any other questions about this patch?
Look forward to your review.

Thanks,
Yang

\
 
 \ /
  Last update: 2021-02-18 13:15    [W:0.153 / U:2.568 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site