From: Konstantin Ananyev <konstantin.ananyev@huawei.com>
To: Stephen Hemminger <stephen@networkplumber.org>
Cc: "dev@dpdk.org" <dev@dpdk.org>,
Wathsala Vithanage <wathsala.vithanage@arm.com>
Subject: RE: [PATCH 2/5] ring: use GCC builtin as alternative to rte_atomic32
Date: Thu, 4 Jun 2026 15:43:32 +0000 [thread overview]
Message-ID: <d2adf4776a53494292bc038d85153d66@huawei.com> (raw)
In-Reply-To: <20260604082010.1fe8a27d@phoenix.local>
> On Thu, 4 Jun 2026 15:11:25 +0000
> Konstantin Ananyev <konstantin.ananyev@huawei.com> wrote:
>
> > > /**
> > > * @internal This is a helper function that moves the producer/consumer
> head
> > > * optimized for single threaded case
> > > @@ -82,7 +81,7 @@ __rte_ring_headtail_move_head_st(struct
> rte_ring_headtail
> > > *d,
> > > /* Single producer: only this thread writes d->head,
> > > * so a relaxed load is sufficient.
> > > */
> > > - *old_head = rte_atomic_load_explicit(&d->head,
> > > rte_memory_order_relaxed);
> > > + *old_head = rte_atomic_load_explicit(&d->head,
> > > rte_memory_order_acquire);
> >
> > Not sure, why it had changed to 'acquire' here?
> > Looks like just patch splitting mistake, no?
>
> I should have kept it as relaxed for the first load.
Yes, I believe so.
In fact, I reverted it back to 'relaxed' in final version (after applying all 5 patches)
and run both stress_ring_autotest and stress_soring_autotest on ARM box in our lab.
All passed.
Konstantin
next prev parent reply other threads:[~2026-06-04 15:43 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-06-02 17:07 [PATCH 0/5] ring: convert to C11 atomics where practical Stephen Hemminger
2026-06-02 17:07 ` [PATCH 1/5] ring: split single thread vs multi-thread cases Stephen Hemminger
2026-06-04 15:09 ` Konstantin Ananyev
2026-06-02 17:07 ` [PATCH 2/5] ring: use GCC builtin as alternative to rte_atomic32 Stephen Hemminger
2026-06-04 15:11 ` Konstantin Ananyev
2026-06-04 15:20 ` Stephen Hemminger
2026-06-04 15:43 ` Konstantin Ananyev [this message]
2026-06-02 17:07 ` [PATCH 3/5] ring: use C11 for update_tail Stephen Hemminger
2026-06-04 15:39 ` Konstantin Ananyev
2026-06-02 17:07 ` [PATCH 4/5] ring: drop unused arg to update_tail Stephen Hemminger
2026-06-04 15:40 ` Konstantin Ananyev
2026-06-02 17:07 ` [PATCH 5/5] ring: use C11 for single thread move head Stephen Hemminger
2026-06-04 15:41 ` Konstantin Ananyev
2026-06-04 16:32 ` [PATCH v2] ring: convert to C11 atomics where practical Stephen Hemminger
2026-06-04 16:32 ` [PATCH v2 1/3] ring: split single thread vs multi-thread cases Stephen Hemminger
2026-06-04 16:32 ` [PATCH v2 2/3] ring: use GCC builtin as alternative to rte_atomic32 Stephen Hemminger
2026-06-04 16:32 ` [PATCH v2 3/3] ring: cleanup the C11 code Stephen Hemminger
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=d2adf4776a53494292bc038d85153d66@huawei.com \
--to=konstantin.ananyev@huawei.com \
--cc=dev@dpdk.org \
--cc=stephen@networkplumber.org \
--cc=wathsala.vithanage@arm.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