From: Alexey Budankov <alexey.budankov@linux.intel.com>
To: Jiri Olsa <jolsa@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>,
Namhyung Kim <namhyung@kernel.org>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>, Andi Kleen <ak@linux.intel.com>,
linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v8 01/13] tools/libperf: avoid moving of fds at fdarray__filter() call
Date: Thu, 25 Jun 2020 22:32:29 +0300 [thread overview]
Message-ID: <688910f3-289e-d63e-79e3-0a17a6df0e9e@linux.intel.com> (raw)
In-Reply-To: <20200625171405.GL2719003@krava>
On 25.06.2020 20:14, Jiri Olsa wrote:
> On Wed, Jun 24, 2020 at 08:19:32PM +0300, Alexey Budankov wrote:
>>
>> On 17.06.2020 11:35, Alexey Budankov wrote:
>>>
>>> Skip fds with zeroed revents field from count and avoid fds moving
>>> at fdarray__filter() call so fds indices returned by fdarray__add()
>>> call stay the same and can be used for direct access and processing
>>> of fd revents status field at entries array of struct fdarray object.
>>>
>>> Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
>>> ---
>>> tools/lib/api/fd/array.c | 11 +++++------
>>> tools/perf/tests/fdarray.c | 20 ++------------------
>>> 2 files changed, 7 insertions(+), 24 deletions(-)
>>>
>>> diff --git a/tools/lib/api/fd/array.c b/tools/lib/api/fd/array.c
>>> index 58d44d5eee31..97843a837370 100644
>>> --- a/tools/lib/api/fd/array.c
>>> +++ b/tools/lib/api/fd/array.c
>>> @@ -93,22 +93,21 @@ int fdarray__filter(struct fdarray *fda, short revents,
>>> return 0;
>>>
>>> for (fd = 0; fd < fda->nr; ++fd) {
>>> + if (!fda->entries[fd].revents)
>>> + continue;
>>> +
>>
>> So it looks like this condition also filters out non signaling events fds, not only
>> control and others fds, and this should be somehow avoided so such event related fds
>> would be counted. Several options have been proposed so far:
>>
>> 1) Explicit typing of fds via API extension and filtering based on the types:
>> a) with separate fdarray__add_stat() call
>> b) with type arg of existing fdarray__add() call
>> c) various memory management design is possible
>>
>> 2) Playing tricks with fd positions inside entries and assumptions on fdarray API calls ordering
>> - looks more like a hack than a designed solution
>>
>> 3) Rewrite of fdarray class to allocate separate object for every added fds
>> - can be replaced with nonscrewing of fds by __filter()
>>
>> 4) Distinct between fds types at fdarray__filter() using .revents == 0 condition
>> - seems to have corner cases and thus not applicable
>>
>> 5) Extension of fdarray__poll(, *arg_ptr, arg_size) with arg of fds array to atomically poll
>> on fdarray_add()-ed fds and external arg fds and then external arg fds processing
>>
>> 6) Rewrite of fdarray class on epoll() call basis
>> - introduces new scalability restrictions for Perf tool
>
> hum, how many fds for polling do you expect in your workloads?
Currently it is several hundreds so default of 1K is easily hit and
"Profile a Large Number of PMU Events on Multi-Core Systems" section [1]
recommends:
soft nofile 65535
hard nofile 65535
for for /etc/security/limits.conf settings.
~Alexey
[1] https://software.intel.com/content/www/us/en/develop/documentation/vtune-cookbook/top/configuration-recipes/profiling-hardware-without-sampling-drivers.html
>
> jirka
>
next prev parent reply other threads:[~2020-06-25 19:32 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-17 8:30 [PATCH v8 00/13] perf: support enable and disable commands in stat and record modes Alexey Budankov
2020-06-17 8:35 ` [PATCH v8 01/13] tools/libperf: avoid moving of fds at fdarray__filter() call Alexey Budankov
2020-06-24 17:19 ` Alexey Budankov
2020-06-25 17:14 ` Jiri Olsa
2020-06-25 19:32 ` Alexey Budankov [this message]
2020-06-26 9:37 ` Jiri Olsa
2020-06-26 10:06 ` Alexey Budankov
2020-06-29 15:11 ` Alexey Budankov
2020-06-29 19:17 ` Jiri Olsa
2020-06-17 8:35 ` [PATCH v8 02/13] perf evlist: introduce control file descriptors Alexey Budankov
2020-06-17 8:36 ` [PATCH v8 03/13] perf evlist: implement control command handling functions Alexey Budankov
2020-06-23 14:56 ` Jiri Olsa
2020-06-23 15:03 ` Arnaldo Carvalho de Melo
2020-06-23 15:14 ` Jiri Olsa
2020-06-24 13:35 ` Alexey Budankov
2020-06-23 14:56 ` Jiri Olsa
2020-06-24 13:20 ` Alexey Budankov
2020-06-17 8:37 ` [PATCH v8 04/13] perf stat: factor out body of event handling loop for system wide Alexey Budankov
2020-06-23 14:56 ` Jiri Olsa
2020-06-24 14:27 ` Alexey Budankov
2020-06-25 12:17 ` Jiri Olsa
2020-06-25 16:01 ` Alexey Budankov
2020-06-25 17:13 ` Jiri Olsa
2020-06-25 18:43 ` Alexey Budankov
2020-06-17 8:38 ` [PATCH v8 05/13] perf stat: move target check to loop control statement Alexey Budankov
2020-06-17 8:39 ` [PATCH v8 06/13] perf stat: factor out body of event handling loop for fork case Alexey Budankov
2020-06-17 8:40 ` [PATCH v8 07/13] perf stat: factor out event handling loop into dispatch_events() Alexey Budankov
2020-06-23 14:56 ` Jiri Olsa
2020-06-24 13:27 ` Alexey Budankov
2020-06-17 8:40 ` [PATCH v8 08/13] perf stat: extend -D,--delay option with -1 value Alexey Budankov
2020-06-17 8:41 ` [PATCH v8 09/13] perf stat: implement control commands handling Alexey Budankov
2020-06-23 14:54 ` Jiri Olsa
2020-06-24 14:10 ` Alexey Budankov
2020-06-25 12:14 ` Jiri Olsa
2020-06-25 14:58 ` Alexey Budankov
2020-06-23 14:54 ` Jiri Olsa
2020-06-24 13:39 ` Alexey Budankov
2020-06-25 12:12 ` Jiri Olsa
2020-06-25 14:52 ` Alexey Budankov
2020-06-17 8:42 ` [PATCH v8 10/13] perf stat: introduce --control fd:ctl-fd[,ack-fd] options Alexey Budankov
2020-06-17 8:42 ` [PATCH v8 11/13] perf record: extend -D,--delay option with -1 value Alexey Budankov
2020-06-17 8:43 ` [PATCH v8 12/13] perf record: implement control commands handling Alexey Budankov
2020-06-23 14:54 ` Jiri Olsa
2020-06-24 14:00 ` Alexey Budankov
2020-06-24 14:55 ` Alexey Budankov
2020-06-25 17:07 ` Jiri Olsa
2020-06-17 8:44 ` [PATCH v8 13/13] perf record: introduce --control fd:ctl-fd[,ack-fd] options Alexey Budankov
2020-06-22 3:38 ` [PATCH v8 00/13] perf: support enable and disable commands in stat and record modes Alexey Budankov
2020-06-22 8:55 ` Jiri Olsa
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=688910f3-289e-d63e-79e3-0a17a6df0e9e@linux.intel.com \
--to=alexey.budankov@linux.intel.com \
--cc=acme@kernel.org \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).