From: "Alexei Starovoitov" <alexei.starovoitov@gmail.com>
To: "Emil Tsalapatis" <emil@etsalapatis.com>, <bpf@vger.kernel.org>
Cc: <andrii@kernel.org>, <eddyz87@gmail.com>, <memxor@gmail.com>,
<daniel@iogearbox.net>
Subject: Re: [PATCH bpf-next v3 6/7] selftests/bpf: libarena: Add a transfer cache
Date: Tue, 27 Oct 2026 19:52:54 +0000 [thread overview]
Message-ID: <DMFVT5P2IT5V.3U8JXPSPQR8CG@gmail.com> (raw)
In-Reply-To: <20261023002056.6647-7-emil@etsalapatis.com>
On Thu, Oct 22, 2026 at 05:20 PM Emil Tsalapatis <emil@etsalapatis.com> wrote:
> When the array is full or its lock is busy, spill the local batch to the
> buddy allocator with buddy_free_bulk(), so the next frees fit in the
> local cache instead of each taking the transfer and buddy locks. NMI
My earlier feedback must have been lost:
Pls add the buddy_free_bulk() spill in patch 5, next to the batched
refill. Keep only the transfer array in this patch, on top of it.
As posted buddy_cache_spill() arrives here with both branches. Until this
patch a free into a full cache takes the buddy lock for every object.
Also your libarena compatibility fixups series changes the same lines of
buddy.h, it seems. I suspect you want them to go first and rebase this one.
pw-bot: cr
next prev parent reply other threads:[~2026-10-27 19:52 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-23 0:20 [PATCH bpf-next v3 0/7] bpf libarena allocator improvements Emil Tsalapatis
2026-10-23 0:20 ` [PATCH bpf-next v3 1/7] selftests/bpf: libarena: Add bulk buddy allocation helpers Emil Tsalapatis
2026-10-23 0:49 ` bot+bpf-ci
2026-10-23 0:20 ` [PATCH bpf-next v3 2/7] selftests/bpf: Add a parallel buddy allocator benchmark Emil Tsalapatis
2026-10-23 0:20 ` [PATCH bpf-next v3 3/7] selftests/bpf: libarena: Add buddy per-CPU caches Emil Tsalapatis
2026-10-23 0:49 ` bot+bpf-ci
2026-10-23 0:20 ` [PATCH bpf-next v3 4/7] selftests/bpf: libarena: Handle NMI reentrancy Emil Tsalapatis
2026-10-27 19:49 ` Alexei Starovoitov
2026-10-27 21:03 ` Emil Tsalapatis
2026-10-23 0:20 ` [PATCH bpf-next v3 5/7] selftests/bpf: libarena: Refill local caches in batches Emil Tsalapatis
2026-10-27 19:50 ` Alexei Starovoitov
2026-10-27 20:57 ` Emil Tsalapatis
2026-10-28 4:51 ` Alexei Starovoitov
2026-10-23 0:20 ` [PATCH bpf-next v3 6/7] selftests/bpf: libarena: Add a transfer cache Emil Tsalapatis
2026-10-27 19:52 ` Alexei Starovoitov [this message]
2026-10-27 20:51 ` Emil Tsalapatis
2026-10-23 0:20 ` [PATCH bpf-next v3 7/7] selftests/bpf: libarena: Cover buddy cache fast paths Emil Tsalapatis
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=DMFVT5P2IT5V.3U8JXPSPQR8CG@gmail.com \
--to=alexei.starovoitov@gmail.com \
--cc=andrii@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=eddyz87@gmail.com \
--cc=emil@etsalapatis.com \
--cc=memxor@gmail.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