From: Jiri Olsa <jolsa@redhat.com>
To: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>,
Namhyung Kim <namhyung@kernel.org>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Adrian Hunter <adrian.hunter@intel.com>,
Andi Kleen <ak@linux.intel.com>,
Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v2 00/15] Introduce threaded trace streaming for basic perf record operation
Date: Sat, 24 Oct 2020 17:43:09 +0200 [thread overview]
Message-ID: <20201024154309.GA2589351@krava> (raw)
In-Reply-To: <1ec29ed6-0047-d22f-630b-a7f5ccee96b4@linux.intel.com>
On Wed, Oct 21, 2020 at 06:52:43PM +0300, Alexey Budankov wrote:
>
> Changes in v2:
> - explicitly added credit tags to patches 6/15 and 15/15,
> additionally to cites [1], [2]
> - updated description of 3/15 to explicitly mention the reason
> to open data directories in read access mode (e.g. for perf report)
> - implemented fix for compilation error of 2/15
> - explicitly elaborated on found issues to be resolved for
> threaded AUX trace capture
>
> v1: https://lore.kernel.org/lkml/810f3a69-0004-9dff-a911-b7ff97220ae0@linux.intel.com/
>
> Patch set provides threaded trace streaming for base perf record
> operation. Provided streaming mode (--threads) mitigates profiling
> data losses and resolves scalability issues of serial and asynchronous
> (--aio) trace streaming modes on multicore server systems. The patch
> set is based on the prototype [1], [2] and the most closely relates
> to mode 3) "mode that creates thread for every monitored memory map".
so what I liked about the previous code was that you could
configure how the threads would be created
default --threads options created thread for each cpu like
in your change:
$ perf record -v --threads ...
...
thread 0 monitor: 0 allowed: 0
thread 1 monitor: 1 allowed: 1
thread 2 monitor: 2 allowed: 2
thread 3 monitor: 3 allowed: 3
thread 4 monitor: 4 allowed: 4
thread 5 monitor: 5 allowed: 5
thread 6 monitor: 6 allowed: 6
thread 7 monitor: 7 allowed: 7
then numa based:
$ perf record -v --threads=numa ...
...
thread 0 monitor: 0-5,12-17 allowed: 0-5,12-17
thread 1 monitor: 6-11,18-23 allowed: 6-11,18-23
socket based:
$ perf record -v --threads=socket ...
...
thread 0 monitor: 0-7 allowed: 0-7
core based:
$ perf record -v --threads=core ...
...
thread 0 monitor: 0,4 allowed: 0,4
thread 1 monitor: 1,5 allowed: 1,5
thread 2 monitor: 2,6 allowed: 2,6
thread 3 monitor: 3,7 allowed: 3,7
and user configurable:
$ perf record -v --threads=0-3/0:4-7/4 ...
...
threads: 0. monitor 0-3, allowed 0
threads: 1. monitor 4-7, allowed 4
so this way you could easily pin threads to cpu/core/socket/numa,
or to some other cpu of your choice, because this will be always
game of try and check where I'm not getting LOST events and not
creating 1000 threads
perf record: Add support for threads numa option value
perf record: Add support for threads socket option value
perf record: Add support for threads core option value
perf record: Add support for threads user option value
jirka
next prev parent reply other threads:[~2020-10-24 15:43 UTC|newest]
Thread overview: 64+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-21 15:52 [PATCH v2 00/15] Introduce threaded trace streaming for basic perf record operation Alexey Budankov
2020-10-21 15:56 ` [PATCH v2 01/15] perf session: introduce trace file path to be shown in raw trace dump Alexey Budankov
2020-10-22 4:28 ` Namhyung Kim
2020-10-21 15:57 ` [PATCH v2 02/15] perf report: output trace file name " Alexey Budankov
2020-10-22 4:29 ` Namhyung Kim
2020-10-21 15:57 ` [PATCH v2 03/15] perf data: open data directory in read access mode Alexey Budankov
2020-10-22 4:31 ` Namhyung Kim
2020-10-22 7:50 ` Alexey Budankov
2020-10-24 15:43 ` Jiri Olsa
2020-10-26 17:47 ` Alexey Budankov
2020-10-27 11:59 ` Jiri Olsa
2020-10-27 14:44 ` Alexey Budankov
2020-10-21 15:59 ` [PATCH v2 04/15] perf session: move reader object definition to header file Alexey Budankov
2020-10-22 4:31 ` Namhyung Kim
2020-10-24 15:44 ` Jiri Olsa
2020-10-26 17:50 ` Alexey Budankov
2020-10-21 16:00 ` [PATCH v2 05/15] perf session: introduce decompressor into trace reader object Alexey Budankov
2020-10-22 4:36 ` Namhyung Kim
2020-10-22 7:20 ` Alexey Budankov
2020-10-24 15:44 ` Jiri Olsa
2020-10-26 8:54 ` Alexei Budankov
2020-10-21 16:01 ` [PATCH v2 06/15] perf session: load data directory into tool process memory Alexey Budankov
2020-10-24 15:43 ` Jiri Olsa
2020-10-27 7:37 ` Alexey Budankov
2020-10-27 12:21 ` Jiri Olsa
2020-10-27 14:43 ` Alexey Budankov
2020-10-28 7:22 ` Namhyung Kim
2020-10-28 15:39 ` Jiri Olsa
2020-10-29 11:00 ` Namhyung Kim
2020-10-28 15:36 ` Jiri Olsa
2020-10-27 15:04 ` Alexey Budankov
2020-10-21 16:01 ` [PATCH v2 07/15] perf record: introduce trace file, compressor and stats in mmap object Alexey Budankov
2020-10-21 16:02 ` [PATCH v2 08/15] perf record: write trace data into mmap trace files Alexey Budankov
2020-10-24 15:44 ` Jiri Olsa
2020-10-26 8:52 ` Alexei Budankov
2020-10-26 10:32 ` Jiri Olsa
2020-10-26 14:04 ` Alexei Budankov
2020-10-21 16:03 ` [PATCH v2 09/15] perf record: introduce thread specific objects for trace streaming Alexey Budankov
2020-10-24 15:44 ` Jiri Olsa
2020-10-26 8:53 ` Alexei Budankov
2020-10-21 16:04 ` [PATCH v2 10/15] perf record: manage thread specific data array Alexey Budankov
2020-10-24 15:44 ` Jiri Olsa
2020-10-26 8:39 ` Alexei Budankov
2020-10-21 16:06 ` [PATCH v2 11/15] perf evlist: introduce evlist__ctlfd_update() to update ctl fd status Alexey Budankov
2020-10-21 16:07 ` [PATCH v2 12/15] perf record: introduce thread local variable for trace streaming Alexey Budankov
2020-10-24 15:43 ` Jiri Olsa
2020-10-26 8:21 ` Alexei Budankov
2020-10-26 10:34 ` Jiri Olsa
2020-10-26 14:11 ` Alexei Budankov
2020-10-27 12:01 ` Jiri Olsa
2020-10-27 14:16 ` Alexey Budankov
2020-10-27 15:58 ` Alexey Budankov
2020-10-21 16:08 ` [PATCH v2 13/15] perf record: stop threads in the end of " Alexey Budankov
2020-10-21 16:10 ` [PATCH v2 14/15] perf record: start threads in the beginning " Alexey Budankov
2020-10-24 15:44 ` Jiri Olsa
2020-10-26 8:39 ` Alexei Budankov
2020-10-21 16:10 ` [PATCH v2 15/15] perf record: introduce --threads command line option Alexey Budankov
2020-10-24 15:43 ` Jiri Olsa [this message]
2020-10-26 17:59 ` [PATCH v2 00/15] Introduce threaded trace streaming for basic perf record operation Alexey Budankov
2020-10-27 12:10 ` Jiri Olsa
2020-10-27 14:26 ` Alexey Budankov
2020-10-27 16:01 ` Alexey Budankov
2020-10-28 7:08 ` Namhyung Kim
[not found] ` <b6150d2f-04a6-9204-59ac-c31c8697c630@linux.intel.com>
2020-10-28 15:32 ` 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=20201024154309.GA2589351@krava \
--to=jolsa@redhat.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=alexey.budankov@linux.intel.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).