From: Andrii Nakryiko <andrii.nakryiko@gmail.com>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>,
Alexei Starovoitov <alexei.starovoitov@gmail.com>,
Florent Revest <revest@chromium.org>,
linux-trace-kernel@vger.kernel.org,
LKML <linux-kernel@vger.kernel.org>,
Martin KaFai Lau <martin.lau@linux.dev>,
bpf <bpf@vger.kernel.org>, Sven Schnelle <svens@linux.ibm.com>,
Alexei Starovoitov <ast@kernel.org>,
Jiri Olsa <jolsa@kernel.org>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Alan Maguire <alan.maguire@oracle.com>,
Mark Rutland <mark.rutland@arm.com>,
Peter Zijlstra <peterz@infradead.org>,
Thomas Gleixner <tglx@linutronix.de>, Guo Ren <guoren@kernel.org>
Subject: Re: [PATCH v9 00/36] tracing: fprobe: function_graph: Multi-function graph and fprobe on fgraph
Date: Mon, 29 Apr 2024 13:28:44 -0700 [thread overview]
Message-ID: <CAEf4BzazmnBOr+sq7w_KeUQpP7v9o+k418tuzCMEbXXbUeg7bQ@mail.gmail.com> (raw)
In-Reply-To: <20240428192549.7898bf6b@rorschach.local.home>
On Sun, Apr 28, 2024 at 4:25 PM Steven Rostedt <rostedt@goodmis.org> wrote:
>
> On Thu, 25 Apr 2024 13:31:53 -0700
> Andrii Nakryiko <andrii.nakryiko@gmail.com> wrote:
>
> I'm just coming back from Japan (work and then a vacation), and
> catching up on my email during the 6 hour layover in Detroit.
>
> > Hey Masami,
> >
> > I can't really review most of that code as I'm completely unfamiliar
> > with all those inner workings of fprobe/ftrace/function_graph. I left
> > a few comments where there were somewhat more obvious BPF-related
> > pieces.
> >
> > But I also did run our BPF benchmarks on probes/for-next as a baseline
> > and then with your series applied on top. Just to see if there are any
> > regressions. I think it will be a useful data point for you.
> >
> > You should be already familiar with the bench tool we have in BPF
> > selftests (I used it on some other patches for your tree).
>
> I should get familiar with your tools too.
>
It's a nifty and self-contained tool to do some micro-benchmarking, I
replied to Masami with a few details on how to build and use it.
> >
> > BASELINE
> > ========
> > kprobe : 24.634 ± 0.205M/s
> > kprobe-multi : 28.898 ± 0.531M/s
> > kretprobe : 10.478 ± 0.015M/s
> > kretprobe-multi: 11.012 ± 0.063M/s
> >
> > THIS PATCH SET ON TOP
> > =====================
> > kprobe : 25.144 ± 0.027M/s (+2%)
> > kprobe-multi : 28.909 ± 0.074M/s
> > kretprobe : 9.482 ± 0.008M/s (-9.5%)
> > kretprobe-multi: 13.688 ± 0.027M/s (+24%)
> >
> > These numbers are pretty stable and look to be more or less representative.
>
> Thanks for running this.
>
> >
> > As you can see, kprobes got a bit faster, kprobe-multi seems to be
> > about the same, though.
> >
> > Then (I suppose they are "legacy") kretprobes got quite noticeably
> > slower, almost by 10%. Not sure why, but looks real after re-running
> > benchmarks a bunch of times and getting stable results.
> >
> > On the other hand, multi-kretprobes got significantly faster (+24%!).
> > Again, I don't know if it is expected or not, but it's a nice
> > improvement.
> >
> > If you have any idea why kretprobes would get so much slower, it would
> > be nice to look into that and see if you can mitigate the regression
> > somehow. Thanks!
>
> My guess is that this patch set helps generic use cases for tracing the
> return of functions, but will likely add more overhead for single use
> cases. That is, kretprobe is made to be specific for a single function,
> but kretprobe-multi is more generic. Hence the generic version will
> improve at the sacrifice of the specific function. I did expect as much.
>
> That said, I think there's probably a lot of low hanging fruit that can
> be done to this series to help improve the kretprobe performance. I'm
> not sure we can get back to the baseline, but I'm hoping we can at
> least make it much better than that 10% slowdown.
That would certainly be appreciated, thanks!
But I'm also considering trying to switch to multi-kprobe/kretprobe
automatically on libbpf side, whenever possible, so that users can get
the best performance. There might still be situations where this can't
be done, so singular kprobe/kretprobe can't be completely deprecated,
but multi variants seems to be universally faster, so I'm going to
make them a default (I need to handle some backwards compat aspect,
but that's libbpf-specific stuff you shouldn't be concerned with).
>
> I'll be reviewing this patch set this week as I recover from jetlag.
>
> -- Steve
next prev parent reply other threads:[~2024-04-29 20:28 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-15 12:48 [PATCH v9 00/36] tracing: fprobe: function_graph: Multi-function graph and fprobe on fgraph Masami Hiramatsu (Google)
2024-04-15 12:49 ` [PATCH v9 01/36] tracing: Add a comment about ftrace_regs definition Masami Hiramatsu (Google)
2024-04-24 12:23 ` Florent Revest
2024-04-24 13:19 ` Florent Revest
2024-04-24 14:31 ` Masami Hiramatsu
2024-04-15 12:49 ` [PATCH v9 02/36] tracing: Rename ftrace_regs_return_value to ftrace_regs_get_return_value Masami Hiramatsu (Google)
2024-04-15 12:49 ` [PATCH v9 03/36] x86: tracing: Add ftrace_regs definition in the header Masami Hiramatsu (Google)
2024-04-15 12:49 ` [PATCH v9 04/36] function_graph: Convert ret_stack to a series of longs Masami Hiramatsu (Google)
2024-04-15 12:49 ` [PATCH v9 05/36] fgraph: Use BUILD_BUG_ON() to make sure we have structures divisible by long Masami Hiramatsu (Google)
2024-04-15 12:50 ` [PATCH v9 06/36] function_graph: Add an array structure that will allow multiple callbacks Masami Hiramatsu (Google)
2024-04-15 12:50 ` [PATCH v9 07/36] function_graph: Allow multiple users to attach to function graph Masami Hiramatsu (Google)
2024-04-20 3:52 ` Steven Rostedt
2024-04-20 8:56 ` Masami Hiramatsu
2024-04-15 12:50 ` [PATCH v9 08/36] function_graph: Remove logic around ftrace_graph_entry and return Masami Hiramatsu (Google)
2024-04-15 12:50 ` [PATCH v9 09/36] ftrace/function_graph: Pass fgraph_ops to function graph callbacks Masami Hiramatsu (Google)
2024-04-15 12:50 ` [PATCH v9 10/36] ftrace: Allow function_graph tracer to be enabled in instances Masami Hiramatsu (Google)
2024-04-15 12:51 ` [PATCH v9 11/36] ftrace: Allow ftrace startup flags exist without dynamic ftrace Masami Hiramatsu (Google)
2024-04-15 12:51 ` [PATCH v9 12/36] function_graph: Have the instances use their own ftrace_ops for filtering Masami Hiramatsu (Google)
2024-04-15 12:51 ` [PATCH v9 13/36] function_graph: Use a simple LRU for fgraph_array index number Masami Hiramatsu (Google)
2024-04-15 12:51 ` [PATCH v9 14/36] function_graph: Add "task variables" per task for fgraph_ops Masami Hiramatsu (Google)
2024-04-15 12:51 ` [PATCH v9 15/36] function_graph: Move set_graph_function tests to shadow stack global var Masami Hiramatsu (Google)
2024-04-15 12:52 ` [PATCH v9 16/36] function_graph: Move graph depth stored data " Masami Hiramatsu (Google)
2024-04-15 12:52 ` [PATCH v9 17/36] function_graph: Move graph notrace bit " Masami Hiramatsu (Google)
2024-04-15 12:52 ` [PATCH v9 18/36] function_graph: Implement fgraph_reserve_data() and fgraph_retrieve_data() Masami Hiramatsu (Google)
2024-04-15 12:52 ` [PATCH v9 19/36] function_graph: Add selftest for passing local variables Masami Hiramatsu (Google)
2024-04-15 12:52 ` [PATCH v9 20/36] ftrace: Add multiple fgraph storage selftest Masami Hiramatsu (Google)
2024-04-15 12:53 ` [PATCH v9 21/36] function_graph: Pass ftrace_regs to entryfunc Masami Hiramatsu (Google)
2024-04-15 12:53 ` [PATCH v9 22/36] function_graph: Replace fgraph_ret_regs with ftrace_regs Masami Hiramatsu (Google)
2024-04-15 12:53 ` [PATCH v9 23/36] function_graph: Pass ftrace_regs to retfunc Masami Hiramatsu (Google)
2024-04-15 12:53 ` [PATCH v9 24/36] fprobe: Use ftrace_regs in fprobe entry handler Masami Hiramatsu (Google)
2024-04-15 12:53 ` [PATCH v9 25/36] fprobe: Use ftrace_regs in fprobe exit handler Masami Hiramatsu (Google)
2024-04-15 12:54 ` [PATCH v9 26/36] tracing: Add ftrace_partial_regs() for converting ftrace_regs to pt_regs Masami Hiramatsu (Google)
2024-04-15 12:54 ` [PATCH v9 27/36] tracing: Add ftrace_fill_perf_regs() for perf event Masami Hiramatsu (Google)
2024-04-15 12:54 ` [PATCH v9 28/36] tracing/fprobe: Enable fprobe events with CONFIG_DYNAMIC_FTRACE_WITH_ARGS Masami Hiramatsu (Google)
2024-04-15 12:54 ` [PATCH v9 29/36] bpf: Enable kprobe_multi feature if CONFIG_FPROBE is enabled Masami Hiramatsu (Google)
2024-04-25 20:09 ` Andrii Nakryiko
2024-04-29 14:57 ` Masami Hiramatsu
2024-04-15 12:54 ` [PATCH v9 30/36] ftrace: Add CONFIG_HAVE_FTRACE_GRAPH_FUNC Masami Hiramatsu (Google)
2024-04-15 12:55 ` [PATCH v9 31/36] fprobe: Rewrite fprobe on function-graph tracer Masami Hiramatsu (Google)
2024-04-15 12:55 ` [PATCH v9 32/36] tracing/fprobe: Remove nr_maxactive from fprobe Masami Hiramatsu (Google)
2024-04-15 12:55 ` [PATCH v9 33/36] selftests: ftrace: Remove obsolate maxactive syntax check Masami Hiramatsu (Google)
2024-04-15 12:55 ` [PATCH v9 34/36] selftests/ftrace: Add a test case for repeating register/unregister fprobe Masami Hiramatsu (Google)
2024-04-15 12:55 ` [PATCH v9 35/36] Documentation: probes: Update fprobe on function-graph tracer Masami Hiramatsu (Google)
2024-04-15 12:55 ` [PATCH v9 36/36] fgraph: Skip recording calltime/rettime if it is not nneeded Masami Hiramatsu (Google)
2024-04-25 20:15 ` Andrii Nakryiko
2024-04-29 14:56 ` Masami Hiramatsu
2024-04-19 5:36 ` [PATCH v9 00/36] tracing: fprobe: function_graph: Multi-function graph and fprobe on fgraph Masami Hiramatsu
2024-04-19 8:01 ` Steven Rostedt
2024-04-24 13:35 ` Florent Revest
2024-04-25 15:10 ` Masami Hiramatsu
2024-04-25 20:31 ` Andrii Nakryiko
2024-04-28 23:25 ` Steven Rostedt
2024-04-29 20:28 ` Andrii Nakryiko [this message]
2024-04-29 13:51 ` Masami Hiramatsu
2024-04-29 20:25 ` Andrii Nakryiko
2024-04-30 13:32 ` Masami Hiramatsu
2024-04-30 16:29 ` Andrii Nakryiko
2024-05-02 2:06 ` Masami Hiramatsu
2024-05-07 21:04 ` Andrii Nakryiko
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=CAEf4BzazmnBOr+sq7w_KeUQpP7v9o+k418tuzCMEbXXbUeg7bQ@mail.gmail.com \
--to=andrii.nakryiko@gmail.com \
--cc=acme@kernel.org \
--cc=alan.maguire@oracle.com \
--cc=alexei.starovoitov@gmail.com \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=guoren@kernel.org \
--cc=jolsa@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-trace-kernel@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=martin.lau@linux.dev \
--cc=mhiramat@kernel.org \
--cc=peterz@infradead.org \
--cc=revest@chromium.org \
--cc=rostedt@goodmis.org \
--cc=svens@linux.ibm.com \
--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 read-only IMAP folder(s) and NNTP newsgroup(s).