From: Leon Hwang <leon.hwang@linux.dev>
To: Jiri Olsa <olsajiri@gmail.com>
Cc: bpf@vger.kernel.org, Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
John Fastabend <john.fastabend@gmail.com>,
Andrii Nakryiko <andrii@kernel.org>,
Eduard Zingerman <eddyz87@gmail.com>,
Kumar Kartikeya Dwivedi <memxor@gmail.com>,
Martin KaFai Lau <martin.lau@linux.dev>,
Song Liu <song@kernel.org>,
Yonghong Song <yonghong.song@linux.dev>,
Emil Tsalapatis <emil@etsalapatis.com>,
Ihor Solodrai <ihor.solodrai@linux.dev>,
Quentin Monnet <qmo@kernel.org>, Shuah Khan <shuah@kernel.org>,
Mykyta Yatsenko <yatsenko@meta.com>,
Avinash Duduskar <avinash.duduskar@gmail.com>,
Anton Protopopov <a.s.protopopov@gmail.com>,
Amery Hung <ameryhung@gmail.com>, Jordan Rife <jordan@jrife.io>,
Rong Tao <rongtao@cestc.cn>, Eyal Birger <eyal.birger@gmail.com>,
Pu Lehui <pulehui@huawei.com>,
Jingguo Tan <tanjingguo@huawei.com>, Lin Ma <malin89@huawei.com>,
linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org,
linux-kselftest@vger.kernel.org
Subject: Re: [PATCH bpf-next v2 00/21] bpf: Add tracing_multi link support for bpf progs
Date: Thu, 15 Oct 2026 09:48:30 +0800 [thread overview]
Message-ID: <09db7d70-b7d4-4cf5-9447-6d16bac10794@linux.dev> (raw)
In-Reply-To: <as_7Jgy_sdTE9M5O@krava>
On 15/10/26 05:59, Jiri Olsa wrote:
> On Mon, Oct 12, 2026 at 11:40:02PM +0800, Leon Hwang wrote:
>> Similar to the tracing_multi link support for kernel functions [1], add
>> support for bpf progs.
>>
>> With this support, I'll be able to enhance the function-graph feature of
>> bpfsnoop [2]. It will trace all bpf progs, including their subprogs, to
>> draw a full function call graph including bpf prog call sites.
>>
>> The attachment could speed-up when there are hundreds of targets. For
>> example, on high CPU core count servers, it probably runs 200 tc-bpf
>> progs as Kubernetes CNI, and each tc-bpf prog might have 4 subprogs.
>> Hence, there will be 1000 targets to trace for bpfsnoop's function-graph
>> feature.
>>
>> With tracing_multi link support for bpf progs, bpfsnoop will be able to
>> attach to all targets quickly.
>>
>> When attaching to 1000 targets, fentry.multi is much faster than fentry
>> on a 16c16g QEMU VM on an AMD EPYC 9745 server.
>>
>> ./bench tracing-multi-attach-progs
>> Setting up benchmark 'tracing-multi-attach-progs'...
>> tracing-multi-attach-progs: prepared 1000 identical BPF program targets
>> tracing-multi-attach-progs: fentry created and attached 1000 programs/links in 338.171ms
>> tracing-multi-attach-progs: fentry.multi created one program and attached one 1000-target link in 47.345ms
>> tracing-multi-attach-progs: fentry.multi creation/attachment speedup is 7.14x
>
> it's faster, but the original attachment is under 1s,
> so not really a problem imo
>
> I guess the api is better for your use case, like having
> less file descriptors open ?
Correct.
The original attachment is fast enough. So there is no need to improve
attachment performance with a large patch series.
Even though the series brings two benefits:
* One bpf link for multiple bpf prog targets.
* Support for all archs that have trampoline support.
But, I also doubt the value of this series.
Thanks,
Leon
next prev parent reply other threads:[~2026-10-15 1:48 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-12 15:40 Leon Hwang
2026-10-12 15:40 ` [PATCH bpf-next v2 01/21] bpf: Initialize ftrace_managed in bpf_trampoline_get() Leon Hwang
2026-10-14 21:43 ` Jiri Olsa
2026-10-12 15:40 ` [PATCH bpf-next v2 02/21] bpf: Drop unnecessary ftrace_location() in register/unregister/modify_fentry_multi() Leon Hwang
2026-10-14 21:43 ` Jiri Olsa
2026-10-12 15:40 ` [PATCH bpf-next v2 03/21] bpf, x86: Factor out bpf_arch_text_poke_prepare_insns() helper on x86_64 Leon Hwang
2026-10-12 15:40 ` [PATCH bpf-next v2 04/21] bpf, x86: Factor out bpf_arch_text_poke_check_ip() " Leon Hwang
2026-10-12 15:40 ` [PATCH bpf-next v2 05/21] bpf, x86: Introduce bpf_arch_text_poke_batch() " Leon Hwang
2026-10-12 15:40 ` [PATCH bpf-next v2 06/21] bpf: Add bpf_text_poke_batch() helper in trampoline Leon Hwang
2026-10-12 16:11 ` bot+bpf-ci
2026-10-12 15:40 ` [PATCH bpf-next v2 07/21] bpf: Check tgt_prog before is_tracing_multi_id() in verifier Leon Hwang
2026-10-12 15:40 ` [PATCH bpf-next v2 08/21] bpf: Move helpers out of CONFIG_HAVE_SINGLE_FTRACE_DIRECT_OPS guard in trampoline Leon Hwang
2026-10-12 16:11 ` bot+bpf-ci
2026-10-12 15:40 ` [PATCH bpf-next v2 09/21] bpf: Add bpf_trampoline_multi_prog_attach/detach() Leon Hwang
2026-10-12 16:33 ` bot+bpf-ci
2026-10-14 21:43 ` Jiri Olsa
2026-10-12 15:40 ` [PATCH bpf-next v2 10/21] bpf: Shrink CONFIG_HAVE_SINGLE_FTRACE_DIRECT_OPS guard scope for bpf_tracing_multi_attach() Leon Hwang
2026-10-12 15:40 ` [PATCH bpf-next v2 11/21] bpf: Add tracing_multi link support for bpf progs Leon Hwang
2026-10-12 16:33 ` bot+bpf-ci
2026-10-14 21:45 ` Jiri Olsa
2026-10-12 15:40 ` [PATCH bpf-next v2 12/21] libbpf: " Leon Hwang
2026-10-12 15:40 ` [PATCH bpf-next v2 13/21] bpf: Add tracing_multi link fdinfo " Leon Hwang
2026-10-12 15:40 ` [PATCH bpf-next v2 14/21] bpf: Add tracing_multi link info " Leon Hwang
2026-10-12 16:33 ` bot+bpf-ci
2026-10-14 21:43 ` Jiri Olsa
2026-10-15 0:24 ` kernel test robot
2026-10-12 15:40 ` [PATCH bpf-next v2 15/21] selftests/bpf: Add tracing_multi bpf prog attach test Leon Hwang
2026-10-12 15:40 ` [PATCH bpf-next v2 16/21] selftests/bpf: Add tracing_multi bpf prog attach failure tests Leon Hwang
2026-10-12 15:40 ` [PATCH bpf-next v2 17/21] selftests/bpf: Add tracing_multi bpf prog cookie test Leon Hwang
2026-10-12 15:40 ` [PATCH bpf-next v2 18/21] selftests/bpf: Add tracing_multi bpf prog rollback test Leon Hwang
2026-10-14 21:44 ` Jiri Olsa
2026-10-12 15:40 ` [PATCH bpf-next v2 19/21] selftests/bpf: Add tracing_multi bpf prog link info test Leon Hwang
2026-10-12 16:11 ` bot+bpf-ci
2026-10-12 15:40 ` [PATCH bpf-next v2 20/21] selftests/bpf: Test tailcall with fentry.multi Leon Hwang
2026-10-12 15:40 ` [PATCH bpf-next v2 21/21] selftests/bpf: Benchmark tracing_multi bpf progs attachment Leon Hwang
2026-10-12 16:33 ` bot+bpf-ci
2026-10-14 21:59 ` [PATCH bpf-next v2 00/21] bpf: Add tracing_multi link support for bpf progs Jiri Olsa
2026-10-15 1:48 ` Leon Hwang [this message]
2026-10-15 19:03 ` Alexei Starovoitov
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=09db7d70-b7d4-4cf5-9447-6d16bac10794@linux.dev \
--to=leon.hwang@linux.dev \
--cc=a.s.protopopov@gmail.com \
--cc=ameryhung@gmail.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=avinash.duduskar@gmail.com \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=eddyz87@gmail.com \
--cc=emil@etsalapatis.com \
--cc=eyal.birger@gmail.com \
--cc=ihor.solodrai@linux.dev \
--cc=john.fastabend@gmail.com \
--cc=jordan@jrife.io \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linux-trace-kernel@vger.kernel.org \
--cc=malin89@huawei.com \
--cc=martin.lau@linux.dev \
--cc=memxor@gmail.com \
--cc=olsajiri@gmail.com \
--cc=pulehui@huawei.com \
--cc=qmo@kernel.org \
--cc=rongtao@cestc.cn \
--cc=shuah@kernel.org \
--cc=song@kernel.org \
--cc=tanjingguo@huawei.com \
--cc=yatsenko@meta.com \
--cc=yonghong.song@linux.dev \
/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
all inboxes | Powered by JetHome®