From: Jiri Olsa <jolsa@redhat.com>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>,
Jiri Olsa <jolsa@kernel.org>,
Arnaldo Carvalho de Melo <acme@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>,
Thomas Gleixner <tglx@linutronix.de>,
"Luis Claudio R. Goncalves" <lclaudio@uudg.org>,
ldv@altlinux.org, esyr@redhat.com,
Frederic Weisbecker <fweisbec@gmail.com>
Subject: Re: [PATCH 1/8] perf: Allow to block process in syscall tracepoints
Date: Fri, 7 Dec 2018 09:44:53 +0100 [thread overview]
Message-ID: <20181207084453.GA1727@krava> (raw)
In-Reply-To: <20181206131946.2c47f556@vmware.local.home>
On Thu, Dec 06, 2018 at 01:19:46PM -0500, Steven Rostedt wrote:
> On Thu, 6 Dec 2018 09:34:00 +0100
> Peter Zijlstra <peterz@infradead.org> wrote:
>
> > >
> > > I don't understand this.. why are we using schedule_timeout() and all
> > > that?
> >
> > Urgh.. in fact, the more I look at this the more I hate it.
> >
> > We want to block in __perf_output_begin(), but we cannot because both
> > tracepoints and perf will have preemptability disabled down there.
> >
> > So what we do is fail the event, fake the lost count and go all the way
> > up that callstack, detect the failure and then poll-wait and retry.
> >
> > And only do this for a few special events... *yuck*
>
> Since this is a special case, we should add a new option to the perf
> system call that, 1 states that it wants the traced process to block
> (and must have PTRACE permission to do so) and 2, after it reads from
> the buffer, it needs to check a bit that says "this process is blocked,
> please wake it up" and then do another perf call to kick the process to
> continue.
so instead of polling the traced process would properly wait for tracer
to kick him again after it reads/frees the buffer
I guess we could use the control mmap page (struct perf_event_mmap_page)
to communicate the 'we are block-ed' message to the tracer and have new
ioctl to wake the waiting process
jirka
>
> I really dislike the polling too. But because this is not a default
> case, and is a new feature, we can add more infrastructure to make it
> work properly, instead of trying to hack the current method into
> something that does something poorly.
>
> -- Steve
next prev parent reply other threads:[~2018-12-07 8:45 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-05 16:05 [RFC 1/8] perf: Block perf calls for system call tracepoints Jiri Olsa
2018-12-05 16:05 ` [PATCH 1/8] perf: Allow to block process in syscall tracepoints Jiri Olsa
2018-12-05 17:35 ` Steven Rostedt
2018-12-05 17:56 ` Jiri Olsa
2018-12-06 8:09 ` Peter Zijlstra
2018-12-06 10:30 ` Jiri Olsa
2018-12-06 8:10 ` Peter Zijlstra
2018-12-06 8:24 ` Jiri Olsa
2018-12-06 10:31 ` Peter Zijlstra
2018-12-06 8:34 ` Peter Zijlstra
2018-12-06 10:31 ` Jiri Olsa
2018-12-06 18:19 ` Steven Rostedt
2018-12-07 8:44 ` Jiri Olsa [this message]
2018-12-07 8:58 ` Peter Zijlstra
2018-12-07 13:41 ` Steven Rostedt
2018-12-07 15:11 ` Peter Zijlstra
2018-12-07 15:49 ` Arnaldo Carvalho de Melo
2018-12-08 10:41 ` Peter Zijlstra
2018-12-08 17:34 ` Steven Rostedt
2018-12-07 20:14 ` Steven Rostedt
2018-12-08 10:44 ` Peter Zijlstra
2018-12-08 17:38 ` Steven Rostedt
2018-12-10 10:18 ` Peter Zijlstra
2018-12-13 0:39 ` Dmitry V. Levin
2018-12-13 1:26 ` Steven Rostedt
2018-12-13 1:49 ` Dmitry V. Levin
2018-12-13 10:01 ` Peter Zijlstra
2018-12-13 10:05 ` Peter Zijlstra
2018-12-13 10:08 ` Peter Zijlstra
2018-12-13 11:29 ` Jiri Olsa
2018-12-06 8:17 ` Peter Zijlstra
2018-12-06 10:27 ` Jiri Olsa
2018-12-05 16:05 ` [PATCH 2/8] perf tools: Sync uapi perf_event.h Jiri Olsa
2018-12-05 16:05 ` [PATCH 3/8] perf record: Add --block option Jiri Olsa
2018-12-05 16:05 ` [PATCH 4/8] perf trace: " Jiri Olsa
2018-12-05 16:05 ` [PATCH 5/8] perf tools: Add block term support for tracepoints Jiri Olsa
2018-12-05 16:05 ` [PATCH 6/8] perf tools: Add ordered_events__flush_time interface Jiri Olsa
2018-12-14 21:00 ` [tip:perf/core] perf ordered_events: " tip-bot for Jiri Olsa
2018-12-18 14:27 ` tip-bot for Jiri Olsa
2018-12-05 16:05 ` [PATCH 7/8] perf trace: Move event delivery to deliver_event function Jiri Olsa
2018-12-14 21:01 ` [tip:perf/core] perf trace: Move event delivery to a new deliver_event() function tip-bot for Jiri Olsa
2018-12-18 14:28 ` tip-bot for Jiri Olsa
2018-12-05 16:05 ` [PATCH 8/8] perf trace: Add ordered processing for --block option Jiri Olsa
2018-12-14 21:02 ` [tip:perf/core] perf trace: Add ordered processing tip-bot for Jiri Olsa
2018-12-18 14:29 ` tip-bot for 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=20181207084453.GA1727@krava \
--to=jolsa@redhat.com \
--cc=acme@kernel.org \
--cc=alexander.shishkin@linux.intel.com \
--cc=esyr@redhat.com \
--cc=fweisbec@gmail.com \
--cc=jolsa@kernel.org \
--cc=lclaudio@uudg.org \
--cc=ldv@altlinux.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
/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).