From: Song Liu <songliubraving@fb.com>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: bpf <bpf@vger.kernel.org>, Networking <netdev@vger.kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Andrii Nakryiko <andrii@kernel.org>,
Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Kernel Team <Kernel-team@fb.com>,
Christoph Hellwig <hch@infradead.org>,
Peter Zijlstra <peterz@infradead.org>, Song Liu <song@kernel.org>
Subject: Re: [PATCH bpf v2 0/3] bpf: invalidate unused part of bpf_prog_pack
Date: Sat, 7 May 2022 06:50:17 +0000 [thread overview]
Message-ID: <719D99A4-3100-49EC-A7D6-6F9CDBA053C4@fb.com> (raw)
In-Reply-To: <57DBEBDB-71AF-4A85-AB8D-8274541E0F3C@fb.com>
> On Apr 27, 2022, at 11:48 PM, Song Liu <songliubraving@fb.com> wrote:
>
> Hi Linus,
>
> Thanks for your thorough analysis of the situation, which make a lot of
> sense.
>
>> On Apr 27, 2022, at 6:45 PM, Linus Torvalds <torvalds@linux-foundation.org> wrote:
>>
>> On Wed, Apr 27, 2022 at 3:24 PM Song Liu <songliubraving@fb.com> wrote:
>>>
>>> Could you please share your suggestions on this set? Shall we ship it
>>> with 5.18?
>>
>> I'd personally prefer to just not do the prog_pack thing at all, since
>> I don't think it was actually in a "ready to ship" state for this
>> merge window, and the hugepage mapping protection games I'm still
>> leery of.
>>
>> Yes, the hugepage protection things probably do work from what I saw
>> when I looked through them, but that x86 vmalloc hugepage code was
>> really designed for another use (non-refcounted device pages), so the
>> fact that it all actually seems surprisingly ok certainly wasn't
>> because the code was designed to do that new case.
>>
>> Does the prog_pack thing work with small pages?
>>
>> Yes. But that wasn't what it was designed for or its selling point, so
>> it all is a bit suspect to me.
>
> prog_pack on small pages can also reduce the direct map fragmentation.
> This is because libbpf uses tiny BPF programs to probe kernel features.
> Before prog_pack, all these BPF programs can fragment the direct map.
> For example, runqslower (tools/bpf/runqslower/) loads total 7 BPF programs
> (3 actual programs and 4 tiny probe programs). All these programs may
> cause direct map fragmentation. With prog_pack, OTOH, these BPF programs
> would fit in a single page (or even share pages with other tools).
Here are some performance data from our web service production benchmark,
which is the biggest service in our fleet. We compare 3 kernels:
nopack: no bpf_prog_pack; IOW, the same behavior as 5.17
4kpack: use bpf_prog_pack on 4kB pages (same as 5.18-rc5)
2mpack: use bpf_prog_pack on 2MB pages
The benchmark measures system throughput under latency constraints.
4kpack provides 0.5% to 0.7% more throughput than nopack.
2mpack provides 0.6% to 0.9% more throughput than nopack.
So the data has confirmed:
1. Direct map fragmentation has non-trivial impact on system performance;
2. While 2MB pages are preferred, bpf_prog_pack on 4kB pages also gives
Significant performance improvements.
Thanks,
Song
next prev parent reply other threads:[~2022-05-07 6:50 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-04-25 20:39 [PATCH bpf v2 0/3] bpf: invalidate unused part of bpf_prog_pack Song Liu
2022-04-25 20:39 ` [PATCH v2 bpf 1/3] bpf: fill new bpf_prog_pack with illegal instructions Song Liu
2022-04-25 20:39 ` [PATCH v2 bpf 2/3] x86/alternative: introduce text_poke_set Song Liu
2022-04-25 20:39 ` [PATCH v2 bpf 3/3] bpf: introduce bpf_arch_text_invalidate for bpf_prog_pack Song Liu
2022-04-27 22:10 ` [PATCH bpf v2 0/3] bpf: invalidate unused part of bpf_prog_pack Song Liu
2022-04-28 1:45 ` Linus Torvalds
2022-04-28 6:48 ` Song Liu
2022-05-07 6:50 ` Song Liu [this message]
2022-05-07 19:36 ` Song Liu
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=719D99A4-3100-49EC-A7D6-6F9CDBA053C4@fb.com \
--to=songliubraving@fb.com \
--cc=Kernel-team@fb.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=hch@infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=song@kernel.org \
--cc=torvalds@linux-foundation.org \
/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).