From: Stephane Eranian <eranian@google.com>
To: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>,
Alexey Budankov <alexey.budankov@linux.intel.com>,
Jiri Olsa <jolsa@kernel.org>, lkml <linux-kernel@vger.kernel.org>,
Ingo Molnar <mingo@kernel.org>,
Namhyung Kim <namhyung@kernel.org>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Adrian Hunter <adrian.hunter@intel.com>,
Andi Kleen <ak@linux.intel.com>, Song Liu <songliubraving@fb.com>
Subject: Re: [RFC/PATCH 00/14] perf record: Add support to store data in directory
Date: Mon, 11 Feb 2019 11:30:07 -0800 [thread overview]
Message-ID: <CABPqkBTOM2gLvv89ywkpWDKniS2L37XhKPjNLtR8WCY3VuYXzw@mail.gmail.com> (raw)
In-Reply-To: <20190211185510.GF3269@kernel.org>
Arnaldo,
On Mon, Feb 11, 2019 at 10:55 AM Arnaldo Carvalho de Melo
<acme@kernel.org> wrote:
>
> Em Mon, Feb 11, 2019 at 10:34:16AM -0800, Stephane Eranian escreveu:
> > Jiri,
> >
> > On Mon, Feb 11, 2019 at 2:20 AM Jiri Olsa <jolsa@redhat.com> wrote:
> > >
> > > On Tue, Feb 05, 2019 at 02:37:27PM +0100, Jiri Olsa wrote:
> > > > On Mon, Feb 04, 2019 at 02:44:37PM -0800, Stephane Eranian wrote:
> > > > > Jiri,
> > > > >
> > > > > While you're looking at the output format, I think it would be good
> > > > > time to simplify the code handling perf.data file.
> > > > > Today, perf record can emit in two formats: file mode or pipe mode.
> > > > > This adds complexity in the code and
> > > > > is error prone as the file mode path is tested more than the pipe mode
> > > > > path. We have run into multiple issues with
> > > > > the pipe mode in recent years. There is no real reason why we need to
> > > > > maintain two formats. If I recall, the pipe format
> > > > > was introduced because on pipes you cannot lseek to update the headers
> > > > > and therefore some of the information present as tables
> > > > > updated on the fly needed to be generated as pseudo records by the
> > > > > tool. I believe that the pipe format covers all the needs and could
> > > > > supersede the file mode format. That would simplify code in perf
> > > > > record and eliminate the risk of errors when new headers
> > > > > are introduced.
> > > >
> > > > yep, I think we have almost all the features covered for pipe mode,
> > > > and we have all necessary events to describe events features
> > > >
> > > > so with some effort we could switch off the superfluos file header
> > > > and use only events to describe events ;-) make sense, I'll check
> > > > on it
> > >
> > > so following features are not synthesized:
> > >
> > > FEAT_OPN(TRACING_DATA, tracing_data, false),
> > > FEAT_OPN(BUILD_ID, build_id, false),
> > > FEAT_OPN(BRANCH_STACK, branch_stack, false),
> > > FEAT_OPN(AUXTRACE, auxtrace, false),
> > > FEAT_OPN(STAT, stat, false),
> > > FEAT_OPN(CACHE, cache, true),
> > >
> > What do you need for BRANCH_STACK?
> >
> > > I think all could be added and worked around with exception
> > > of BUILD_ID, which we store at the end (after processing
> > > all data) and we need it early in the report phase
> > >
> > Buildids are injected after the fact via perf inject when in pipe mode.
> >
> > > maybe it's time to re-think that buildid -> mmap event
> > > association again, because it's pain in current implementation
> > > as well
> > >
> > Sure, but what do you propose?
>
> this keeps resurfacing, the idea is to have the building go together
> with the PERF_RECORD_MMAP3 event, i.e. as part of setting up an
> executable mapping the loader would get the buildid and ask the kernel
> to keep it aroung, then when a PERF_RECORD_MMAP needs to be issued, it
> can include the build id, so tooling will not need to get it.
>
And how would the dynamic loader (ld.so) communicate the buildid to the kernel?
How would that work for statically linked binaries.
I think you're say the kernel would parse the ELF header looking for
that note section
and extract the buildid from there. Is that what you are proposing?
> Alternatively, we would have a separate thread to process
> PERF_RECORD_MMAP events, and as soon as it gets one from the kernel,
> augment it straight away with the build-id it reads from the ELF file,
> i.e. no need to have the kernel provide it, do it just like we do with
> PERF_RECORD_BPF_EVENT, which reminds me Song probably already posted
> thise bits...
>
But that would not work in pipe mode, wouldn't it?
Unless that thread intercepts everything pushed to the pipe looking
for MMAP records.
> > > looks like bpf code is actualy getting build ids and storing
> > > it for the callchains in kernel.. we can check if we can do
> > > something similar for mmap events
> > >
> > > jirka
>
> --
>
> - Arnaldo
next prev parent reply other threads:[~2019-02-11 19:30 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-02-03 15:30 [RFC/PATCH 00/14] perf record: Add support to store data in directory Jiri Olsa
2019-02-03 15:30 ` [PATCH 01/14] perf tools: Make rm_rf to remove single file Jiri Olsa
2019-02-05 11:33 ` Alexey Budankov
2019-02-05 13:38 ` Jiri Olsa
2019-02-03 15:30 ` [PATCH 02/14] perf session: Add process callback to reader object Jiri Olsa
2019-02-03 15:30 ` [PATCH 03/14] perf data: Move size to struct perf_data_file Jiri Olsa
2019-02-03 15:30 ` [PATCH 04/14] perf data: Add global path holder Jiri Olsa
2019-02-03 15:30 ` [PATCH 05/14] perf data: Make check_backup work over directories Jiri Olsa
2019-02-03 15:30 ` [PATCH 06/14] perf data: Add perf_data__(create_dir|free_dir) functions Jiri Olsa
2019-02-05 11:52 ` Alexey Budankov
2019-02-05 13:42 ` Jiri Olsa
2019-02-05 13:46 ` Arnaldo Carvalho de Melo
2019-02-05 13:53 ` Jiri Olsa
2019-02-03 15:30 ` [PATCH 07/14] perf data: Add perf_data__open_dir_data function Jiri Olsa
2019-02-03 15:30 ` [PATCH 08/14] perf data: Add directory support Jiri Olsa
2019-02-03 15:30 ` [PATCH 09/14] perf data: Don't store auxtrace index for directory data file Jiri Olsa
2019-02-03 15:30 ` [PATCH 10/14] perf data: Add perf_data__update_dir function Jiri Olsa
2019-02-03 15:30 ` [PATCH 11/14] perf data: Make perf_data__size to work over directory Jiri Olsa
2019-02-03 15:30 ` [PATCH 12/14] perf session: Add __perf_session__process_dir_events function Jiri Olsa
2019-02-03 15:30 ` [PATCH 13/14] perf session: Add path to reader object Jiri Olsa
2019-02-03 15:30 ` [PATCH 14/14] perf record: Add --dir option to store data in directory Jiri Olsa
2019-02-05 12:36 ` Alexey Budankov
2019-02-05 13:51 ` Jiri Olsa
2019-02-04 10:12 ` [RFC/PATCH 00/14] perf record: Add support " Alexey Budankov
2019-02-04 10:36 ` Jiri Olsa
2019-02-04 11:29 ` Alexey Budankov
2019-02-04 11:41 ` Jiri Olsa
2019-02-04 18:56 ` Stephane Eranian
2019-02-04 19:27 ` Arnaldo Carvalho de Melo
2019-02-04 19:56 ` Alexey Budankov
2019-02-04 20:05 ` Stephane Eranian
2019-02-04 20:28 ` Jiri Olsa
2019-02-04 22:44 ` Stephane Eranian
2019-02-05 13:37 ` Jiri Olsa
2019-02-11 10:19 ` Jiri Olsa
2019-02-11 18:34 ` Stephane Eranian
2019-02-11 18:53 ` Jiri Olsa
2019-02-11 19:32 ` Arnaldo Carvalho de Melo
2019-02-11 20:18 ` Jiri Olsa
2019-02-11 20:43 ` Stephane Eranian
2019-02-14 11:34 ` Jiri Olsa
2019-02-14 12:57 ` Arnaldo Carvalho de Melo
2019-02-14 13:26 ` Jiri Olsa
2019-02-14 13:59 ` Arnaldo Carvalho de Melo
2019-02-14 21:30 ` Stephane Eranian
[not found] ` <CA+JHD90ssKi3CJ7yfCFTkrS8xwUsZhvd0t7cSCy1MF7TJ2XLYw@mail.gmail.com>
2019-02-14 21:39 ` Stephane Eranian
2019-02-11 18:55 ` Arnaldo Carvalho de Melo
2019-02-11 19:30 ` Stephane Eranian [this message]
2019-02-11 20:30 ` Song Liu
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=CABPqkBTOM2gLvv89ywkpWDKniS2L37XhKPjNLtR8WCY3VuYXzw@mail.gmail.com \
--to=eranian@google.com \
--cc=a.p.zijlstra@chello.nl \
--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=jolsa@kernel.org \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=songliubraving@fb.com \
/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).