From: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
To: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Hemant Kumar <hemant@linux.vnet.ibm.com>,
Adrian Hunter <adrian.hunter@intel.com>,
Mark Wielaard <mjw@redhat.com>, David Ahern <dsahern@gmail.com>,
Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
linux-kernel@vger.kernel.org, srikar@linux.vnet.ibm.com,
peterz@infradead.org, oleg@redhat.com,
hegdevasant@linux.vnet.ibm.com, mingo@redhat.com,
systemtap@sourceware.org, aravinda@linux.vnet.ibm.com,
penberg@iki.fi, brendan.d.gregg@gmail.com, acme@kernel.org,
"yrl.pp-manager.tt@hitachi.com" <yrl.pp-manager.tt@hitachi.com>
Subject: Re: [RFC] perf-cache command interface design
Date: Sat, 08 Nov 2014 04:26:00 -0000 [thread overview]
Message-ID: <545D9B7D.6070307@hitachi.com> (raw)
In-Reply-To: <20141107143804.GA2137@redhat.com>
(2014/11/07 23:38), Arnaldo Carvalho de Melo wrote:
> Em Fri, Nov 07, 2014 at 05:21:08PM +0900, Masami Hiramatsu escreveu:
>> Hello,
>>
>> Here, I've tried to describe my idea of perf-cache subcommand interface.
>> It is just a design review, not implemented yet :)
>> Please give me your comments/ideas!
>>
>> Command-line Synopsis
>> =====================
>>
>> Current "perf buildid-cache [options]" are directly mapped to
>> "perf cache --buildid [options]".
>>
>> And adding --sdt for managing SDT caches as below.
>
> Can't we avoid having to specify the content? I.e. the tool can surely
> be smart enough to figure that out, no?
>
> We should, as much as possible, to make things more compact yet
> unambiguous, IMHO.
Agreed.
>
>> Add or update SDT events in <FILES>
>> perf cache --sdt --add|--update <FILES>
>
> Can automagically figure this out, so, it would become just:
>
> Add or update events in <FILES>
>
> perf cache --add/--update <FILES>
Ah, nice idea :-)
>
>> Remove all SDT events for <FILES>
>> perf cache --sdt --remove <FILES>
>
> Ditto.
>
>> List all SDT events
>> perf cache --sdt --list
>
> That is ok, since the cache can hold different types of contents, but:
>
> perf cache --list
>
> should show everything, with some marking showing the content type.
Yeah, as I replied to Hemant, --sdt/--probe can be unified.
>
>> And --probes for managing probe-caches as below.
>>
>> Add new probe-cache entries for kernel, <PATH> or <MOD>.
>> perf cache --probe [--exec <PATH>|--module <MOD>] --add <SPEC>
>
> No need to specify --probe
>
>> Delete existing probe-cache entries for kernel, <PATH> or/and <BUILDID>.
>> perf cache --probe --del [<GROUP>:]<EVENT>[@<PATH>][#<BUILDID>]
>
> Ditto
>
>> Or remove all entires for given FILES
>> perf cache --probe --remove <FILES>
>
> Ok
>
>> List the probe caches(including SDT) for kernel, <PATH>, or/and <BUILDID>.
>> perf cache --probe --list [@<PATH>][#<BUILDID>]
>
> Can figure out the kind by the initial character, so no need to specify
> --probe
OK.
>> Query the probe definitions.
>> perf cache --probe --query [<GROUP>:]<EVENT>[@<PATH>][#<BUILDID>]
>
> Ditto
>
>> Note that --probes also can be used for managing SDT events, which has % prefix
>> e.g.
>> Add all SDT events for <PATH>
>> perf cache --probe --exec <PATH> --add '%*:*'
>
> See? --probe is smart enough to deal with SDT and probe caches, it can
> disambiguate by looking at the first char.
OK, but --add already have FILES arguments (according to buildid-cache)
So I'd like to move that pattern argument to --probe as I've described
in previous reply to Hemant.
>
>> Remove some SDT events for <PATH>
>> perf cache --probe --del '%some:events@<PATH>'
>
> No need for --probe
>
>> Or remove all SDT events for <BUILDID>
>> perf cache --probe --del '%*:*#<BUILDID>'
>
> Ditto
>
>>
>> File Format
>> ===========
>> All the cache files are placed under ~/.debug/ by default.
>> The paths of buildid cache of binary/symbols are not changed.
>>
>> The SDT/probe caches are placed under the ~/.debug/.probes/path/to/bin/bu/ildid
>
> Here I think we could group everything related to a /path/to/bin into:
>
> ~/.debug/path/to/bin/bu/ild/
>
> With one file per content type:
>
> ~/.debug/path/to/bin/bu/ild/elf
> ~/.debug/path/to/bin/bu/ild/probe
Ah, OK, this is good for me too. :)
>
> That leaves room for us to add more file formats (CTF anyone? The Dtrace
> one, Compact C Type Information, I mean).
Perhaps.
> So that if we wanted to pick everything related to a pathname we could
> do:
>
> tar cf gcc.debug.tar ~/.debug/usr/bin/gcc/
>
> If we instead wanted to pick all files to a specific gcc build id, we
> would do:
>
> tar cf gcc.debug.tar ~/.debug/usr/bin/gcc/bu/ild/
OK.
>> and that is linked to ~/.debug/.probes/.buildid/bu/ildid
>
> Since this would break compatibility with the existing cache format, we
> could as well allow collecting everything related to a build id, by
> making the link be also in this fashion:
>
> tar cf bu.ildid.tar ~/.debug/.build-id/bu/ildid/
>
> Because we would have:
>
> ~/.debug/.build-id/bu/ildid/elf -> ~/.debug/usr/bin/gcc/bu/ild/elf
> ~/.debug/.build-id/bu/ildid/probe -> ~/.debug/usr/bin/gcc/bu/ild/probe
>
> And also links to the files that have no pathnames:
>
> ~/.debug/.build-id/bu/ildid/vdso -> ~/.debug/[vdso]/bu/ild
> ~/.debug/.build-id/bu/ildid/kallsyms -> ~/.debug/[kernel.kallsyms]/bu/ild
> ~/.debug/.build-id/bu/ildid/kcore -> ~/.debug/[kcore]/bu/ild
OK, so let's make bu/ildid to a directory :)
Thank you!
--
Masami HIRAMATSU
Software Platform Research Dept. Linux Technology Research Center
Hitachi, Ltd., Yokohama Research Laboratory
E-mail: masami.hiramatsu.pt@hitachi.com
next prev parent reply other threads:[~2014-11-08 4:26 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-11-02 12:40 [PATCH v4 0/5] perf/sdt: SDT events listing/probing Hemant Kumar
2014-11-02 12:41 ` [PATCH v4 1/5] perf/sdt: ELF support for SDT Hemant Kumar
2014-11-02 12:42 ` [PATCH v4 2/5] perf/sdt: Add SDT events into a cache Hemant Kumar
2014-11-02 12:42 ` [PATCH v4 4/5] perf/sdt: Delete SDT events from cache Hemant Kumar
2014-11-02 12:42 ` [PATCH v4 3/5] perf/sdt: Show SDT cache contents Hemant Kumar
2014-11-02 12:43 ` [PATCH v4 5/5] perf/sdt: Add support to perf record to trace SDT events Hemant Kumar
2014-11-04 7:38 ` Namhyung Kim
2014-11-04 8:06 ` Hemant Kumar
2014-11-04 12:57 ` Masami Hiramatsu
[not found] ` <5459BD3E.7010804@linux.vnet.ibm.com>
2014-11-05 6:51 ` Hemant Kumar
2014-11-05 9:07 ` Masami Hiramatsu
2014-11-05 13:28 ` Arnaldo Carvalho de Melo
2014-11-05 7:06 ` Namhyung Kim
2014-11-05 9:05 ` Masami Hiramatsu
2014-11-06 2:16 ` Josh Stone
2014-11-06 5:34 ` Masami Hiramatsu
2014-11-06 7:06 ` Hemant Kumar
2014-11-06 14:56 ` Masami Hiramatsu
2014-11-07 8:21 ` [RFC] perf-cache command interface design Masami Hiramatsu
2014-11-07 8:42 ` Peter Zijlstra
2014-11-07 13:58 ` [PATCH RESEND 1/2] perf tools: Move disable_buildid_cache() to util/build-id.c Namhyung Kim
2014-11-07 13:58 ` [PATCH 2/2] perf tools: Add record.use-buildid-cache config option Namhyung Kim
2014-11-07 15:16 ` [RFC] perf-cache command interface design David Ahern
2014-11-07 15:33 ` Arnaldo Carvalho de Melo
2014-11-07 10:51 ` Hemant Kumar
2014-11-08 4:15 ` Masami Hiramatsu
2014-11-07 14:38 ` Arnaldo Carvalho de Melo
2014-11-08 4:26 ` Masami Hiramatsu [this message]
2014-11-07 14:43 ` Namhyung Kim
2014-11-08 4:38 ` Masami Hiramatsu
2014-11-10 10:59 ` Masami Hiramatsu
2014-11-10 12:23 ` Arnaldo Carvalho de Melo
2014-11-11 6:53 ` Masami Hiramatsu
2014-11-11 13:10 ` Arnaldo Carvalho de Melo
2014-11-12 15:26 ` Masami Hiramatsu
2014-11-17 3:09 ` Namhyung Kim
2014-11-17 3:17 ` Masami Hiramatsu
2014-11-17 22:09 ` Masami Hiramatsu
2014-11-18 4:51 ` Namhyung Kim
2014-11-18 11:16 ` Masami Hiramatsu
2014-11-18 4:41 ` Namhyung Kim
2014-11-18 10:32 ` Masami Hiramatsu
2014-11-17 18:59 ` Arnaldo Carvalho de Melo
2014-11-18 4:46 ` Namhyung Kim
2014-11-10 12:05 ` Hagen Paul Pfeifer
2014-11-10 12:31 ` Arnaldo Carvalho de Melo
2014-11-10 12:50 ` Peter Zijlstra
2014-11-10 13:37 ` Hagen Paul Pfeifer
2014-11-05 18:24 ` [PATCH v4 5/5] perf/sdt: Add support to perf record to trace SDT events Hemant Kumar
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=545D9B7D.6070307@hitachi.com \
--to=masami.hiramatsu.pt@hitachi.com \
--cc=acme@kernel.org \
--cc=acme@redhat.com \
--cc=adrian.hunter@intel.com \
--cc=aravinda@linux.vnet.ibm.com \
--cc=brendan.d.gregg@gmail.com \
--cc=dsahern@gmail.com \
--cc=hegdevasant@linux.vnet.ibm.com \
--cc=hemant@linux.vnet.ibm.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=mjw@redhat.com \
--cc=namhyung@kernel.org \
--cc=oleg@redhat.com \
--cc=penberg@iki.fi \
--cc=peterz@infradead.org \
--cc=srikar@linux.vnet.ibm.com \
--cc=systemtap@sourceware.org \
--cc=yrl.pp-manager.tt@hitachi.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 read-only IMAP folder(s) and NNTP newsgroup(s).