netdev - Re: [PATCH v2 bpf-next 1/2] bpftool: introduce "prog profile" command

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <72fc922e-68be-e63d-0488-b8bd35e7213b@fb.com>
Date:   Sat, 29 Feb 2020 20:14:29 -0800
From:   Yonghong Song <yhs@...com>
To:     Song Liu <songliubraving@...com>, <netdev@...r.kernel.org>,
        <bpf@...r.kernel.org>
CC:     <kernel-team@...com>, <ast@...nel.org>, <daniel@...earbox.net>,
        <arnaldo.melo@...il.com>, <jolsa@...nel.org>
Subject: Re: [PATCH v2 bpf-next 1/2] bpftool: introduce "prog profile" command



On 2/28/20 3:40 PM, Song Liu wrote:
> With fentry/fexit programs, it is possible to profile BPF program with
> hardware counters. Introduce bpftool "prog profile", which measures key
> metrics of a BPF program.
> 
> bpftool prog profile command creates per-cpu perf events. Then it attaches
> fentry/fexit programs to the target BPF program. The fentry program saves
> perf event value to a map. The fexit program reads the perf event again,
> and calculates the difference, which is the instructions/cycles used by
> the target program.
> 
> Example input and output:
> 
>    ./bpftool prog profile 3 id 337 cycles instructions llc_misses
> 
>          4228 run_cnt
>       3403698 cycles                                              (84.08%)
>       3525294 instructions   #  1.04 insn per cycle               (84.05%)
>            13 llc_misses     #  3.69 LLC misses per million isns  (83.50%)

if run_cnt is 0, the following is the result:

-bash-4.4$ sudo ./bpftool prog profile 3 id 52 cycles instructions 
llc_misses

                  0 run_cnt
                  0 cycles 

                  0 instructions        #     -nan insn per cycle 

                  0 llc_misses          #     -nan LLC misses per 
million isns

-nan is a little bit crypto for user output. maybe just says
   unknown insns per cycle
in the comment?

We can still display "0 cycles" etc. just to make output uniform.

> 
> This command measures cycles and instructions for BPF program with id
> 337 for 3 seconds. The program has triggered 4228 times. The rest of the
> output is similar to perf-stat. In this example, the counters were only
> counting ~84% of the time because of time multiplexing of perf counters.
> 
> Note that, this approach measures cycles and instructions in very small
> increments. So the fentry/fexit programs introduce noticeable errors to
> the measurement results.
> 
> The fentry/fexit programs are generated with BPF skeletons. Therefore, we
> build bpftool twice. The first time _bpftool is built without skeletons.
> Then, _bpftool is used to generate the skeletons. The second time, bpftool
> is built with skeletons.
> 
> Signed-off-by: Song Liu <songliubraving@...com>
> ---
>   tools/bpf/bpftool/Makefile                |  18 +
>   tools/bpf/bpftool/prog.c                  | 428 +++++++++++++++++++++-
>   tools/bpf/bpftool/skeleton/profiler.bpf.c | 171 +++++++++
>   tools/bpf/bpftool/skeleton/profiler.h     |  47 +++
>   tools/scripts/Makefile.include            |   1 +
>   5 files changed, 664 insertions(+), 1 deletion(-)
>   create mode 100644 tools/bpf/bpftool/skeleton/profiler.bpf.c
>   create mode 100644 tools/bpf/bpftool/skeleton/profiler.h
[.....]