From: "Alexei Starovoitov" <alexei.starovoitov@gmail.com>
To: "Puranjay Mohan" <puranjay@kernel.org>, <bpf@vger.kernel.org>
Cc: "Puranjay Mohan" <puranjay12@gmail.com>,
"Alexei Starovoitov" <ast@kernel.org>,
"Andrii Nakryiko" <andrii@kernel.org>,
"Daniel Borkmann" <daniel@iogearbox.net>,
"Martin KaFai Lau" <martin.lau@kernel.org>,
"Eduard Zingerman" <eddyz87@gmail.com>,
"Kumar Kartikeya Dwivedi" <memxor@gmail.com>,
"Mykyta Yatsenko" <mykyta.yatsenko5@gmail.com>,
"Fei Chen" <feichen@meta.com>,
"Taruna Agrawal" <taragrawal@meta.com>,
"Nikhil Dixit Limaye" <ndixit@meta.com>,
"Nikita V. Shirokov" <tehnerd@tehnerd.com>,
<kernel-team@meta.com>
Subject: Re: [RFC PATCH bpf-next 2/6] selftests/bpf: Add BPF batch-timing library
Date: Tue, 21 Apr 2026 18:10:59 -0700 [thread overview]
Message-ID: <DHZA7QEOVHFP.TYQTEC54FX0A@gmail.com> (raw)
In-Reply-To: <20260420111726.2118636-3-puranjay@kernel.org>
On Mon Apr 20, 2026 at 4:17 AM PDT, Puranjay Mohan wrote:
> +#define BENCH_BPF_LOOP(body, reset) ({ \
> + __u64 __bench_start = bpf_get_cpu_time_counter(); \
> + int __bench_result; \
> + \
> + bpf_repeat(batch_iters) { \
> + __bench_result = (body); \
> + reset; \
> + } \
You're trying to save a nsec by relying on bpf_get_cpu_time_counter,
but then wasting a lot more by using bpf_repeat.
It should have been bpf_ktime_get_ns().
I see no value in bpf_get_cpu_time_counter() here.
I bet the numbers should be the same.
But please use plain loop and may_goto if necessary.
For tiny (body) it may be noticeable.
> + \
> + bench_record_sample(bpf_cpu_time_counter_to_ns( \
> + bpf_get_cpu_time_counter() - __bench_start)); \
> + \
> + __bench_result = (body); \
> + __bench_result; \
> +})
> +
> +#endif /* __BENCH_BPF_TIMING_BPF_H__ */
next prev parent reply other threads:[~2026-04-22 1:11 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-20 11:17 [RFC PATCH bpf-next 0/6] selftests/bpf: Add XDP load-balancer benchmark Puranjay Mohan
2026-04-20 11:17 ` [RFC PATCH bpf-next 1/6] selftests/bpf: Add bench_force_done() for early benchmark completion Puranjay Mohan
2026-04-20 12:41 ` sashiko-bot
2026-04-20 15:32 ` Mykyta Yatsenko
2026-04-20 11:17 ` [RFC PATCH bpf-next 2/6] selftests/bpf: Add BPF batch-timing library Puranjay Mohan
2026-04-20 13:18 ` sashiko-bot
2026-04-22 1:10 ` Alexei Starovoitov [this message]
2026-04-20 11:17 ` [RFC PATCH bpf-next 3/6] selftests/bpf: Add XDP load-balancer common definitions Puranjay Mohan
2026-04-20 13:26 ` sashiko-bot
2026-04-20 11:17 ` [RFC PATCH bpf-next 4/6] selftests/bpf: Add XDP load-balancer BPF program Puranjay Mohan
2026-04-20 13:57 ` sashiko-bot
2026-04-20 11:17 ` [RFC PATCH bpf-next 5/6] selftests/bpf: Add XDP load-balancer benchmark driver Puranjay Mohan
2026-04-20 17:11 ` sashiko-bot
2026-04-20 11:17 ` [RFC PATCH bpf-next 6/6] selftests/bpf: Add XDP load-balancer benchmark run script Puranjay Mohan
2026-04-20 17:36 ` sashiko-bot
2026-04-22 1:16 ` [RFC PATCH bpf-next 0/6] selftests/bpf: Add XDP load-balancer benchmark 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=DHZA7QEOVHFP.TYQTEC54FX0A@gmail.com \
--to=alexei.starovoitov@gmail.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=eddyz87@gmail.com \
--cc=feichen@meta.com \
--cc=kernel-team@meta.com \
--cc=martin.lau@kernel.org \
--cc=memxor@gmail.com \
--cc=mykyta.yatsenko5@gmail.com \
--cc=ndixit@meta.com \
--cc=puranjay12@gmail.com \
--cc=puranjay@kernel.org \
--cc=taragrawal@meta.com \
--cc=tehnerd@tehnerd.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