From: Yunsheng Lin <linyunsheng@huawei.com>
To: Cong Wang <xiyou.wangcong@gmail.com>
Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>,
"Toke Høiland-Jørgensen" <toke@redhat.com>,
"Jakub Kicinski" <kuba@kernel.org>,
"David Miller" <davem@davemloft.net>,
"Vladimir Oltean" <olteanv@gmail.com>,
"Alexei Starovoitov" <ast@kernel.org>,
"Daniel Borkmann" <daniel@iogearbox.net>,
"Andrii Nakryiko" <andriin@fb.com>,
"Eric Dumazet" <edumazet@google.com>,
"Wei Wang" <weiwan@google.com>,
"Cong Wang ." <cong.wang@bytedance.com>,
"Taehee Yoo" <ap420073@gmail.com>,
"Linux Kernel Network Developers" <netdev@vger.kernel.org>,
LKML <linux-kernel@vger.kernel.org>,
linuxarm@openeuler.org, "Marc Kleine-Budde" <mkl@pengutronix.de>,
linux-can@vger.kernel.org
Subject: Re: [Linuxarm] Re: [RFC v2] net: sched: implement TCQ_F_CAN_BYPASS for lockless qdisc
Date: Wed, 24 Mar 2021 10:36:45 +0800 [thread overview]
Message-ID: <750de5f8-ff1a-a300-e5b5-8381893e2db9@huawei.com> (raw)
In-Reply-To: <CAM_iQpVgARDaUd3jdvSA11j=Q_K6KvcKfn7DQavGYXUWmvLZtw@mail.gmail.com>
On 2021/3/24 9:49, Cong Wang wrote:
> On Sun, Mar 21, 2021 at 5:55 PM Yunsheng Lin <linyunsheng@huawei.com> wrote:
>>
>> On 2021/3/20 2:15, Cong Wang wrote:
>>> On Thu, Mar 18, 2021 at 12:33 AM Yunsheng Lin <linyunsheng@huawei.com> wrote:
>>>>
>>>> On 2021/3/17 21:45, Jason A. Donenfeld wrote:
>>>>> On 3/17/21, Toke Høiland-Jørgensen <toke@redhat.com> wrote:
>>>>>> Cong Wang <xiyou.wangcong@gmail.com> writes:
>>>>>>
>>>>>>> On Mon, Mar 15, 2021 at 2:07 PM Jakub Kicinski <kuba@kernel.org> wrote:
>>>>>>>>
>>>>>>>> I thought pfifo was supposed to be "lockless" and this change
>>>>>>>> re-introduces a lock between producer and consumer, no?
>>>>>>>
>>>>>>> It has never been truly lockless, it uses two spinlocks in the ring
>>>>>>> buffer
>>>>>>> implementation, and it introduced a q->seqlock recently, with this patch
>>>>>>> now we have priv->lock, 4 locks in total. So our "lockless" qdisc ends
>>>>>>> up having more locks than others. ;) I don't think we are going to a
>>>>>>> right direction...
>>>>>>
>>>>>> Just a thought, have you guys considered adopting the lockless MSPC ring
>>>>>> buffer recently introduced into Wireguard in commit:
>>>>>>
>>>>>> 8b5553ace83c ("wireguard: queueing: get rid of per-peer ring buffers")
>>>>>>
>>>>>> Jason indicated he was willing to work on generalising it into a
>>>>>> reusable library if there was a use case for it. I haven't quite though
>>>>>> through the details of whether this would be such a use case, but
>>>>>> figured I'd at least mention it :)
>>>>>
>>>>> That offer definitely still stands. Generalization sounds like a lot of fun.
>>>>>
>>>>> Keep in mind though that it's an eventually consistent queue, not an
>>>>> immediately consistent one, so that might not match all use cases. It
>>>>> works with wg because we always trigger the reader thread anew when it
>>>>> finishes, but that doesn't apply to everyone's queueing setup.
>>>>
>>>> Thanks for mentioning this.
>>>>
>>>> "multi-producer, single-consumer" seems to match the lockless qdisc's
>>>> paradigm too, for now concurrent enqueuing/dequeuing to the pfifo_fast's
>>>> queues() is not allowed, it is protected by producer_lock or consumer_lock.
>>>>
>>>> So it would be good to has lockless concurrent enqueuing, while dequeuing
>>>> can be protected by qdisc_lock() or q->seqlock, which meets the "multi-producer,
>>>> single-consumer" paradigm.
>>>
>>> I don't think so. Usually we have one queue for each CPU so we can expect
>>> each CPU has a lockless qdisc assigned, but we can not assume this in
>>> the code, so we still have to deal with multiple CPU's sharing a lockless qdisc,
>>> and we usually enqueue and dequeue in process context, so it means we could
>>> have multiple producers and multiple consumers.
>>
>> For lockless qdisc, dequeuing is always within the qdisc_run_begin() and
>> qdisc_run_end(), so multiple consumers is protected with each other by
>> q->seqlock .
>
> So are you saying you will never go lockless for lockless qdisc? I thought
> you really want to go lockless with Jason's proposal of MPMC ring buffer
> code.
I think we has different definition about lockless qdisc.
For my understanding, the dequeuing is within the qdisc_run_begin()
and qdisc_run_end(), so it is always protected by q->seqlock for
lockless qdisck currently, and by lockless qdisc, I never mean
lockless dequeuing, and I am not proposing lockless dequeuing
currently.
Current lockless qdisc for pfifo_fast only means there is no lock
for protection between dequeuing and enqueuing, which also means
when __qdisc_run() is dequeuing a skb while other cpu is enqueuing
a skb.
But enqueuing is protected by producer_lock in skb_array_produce(),
so only one cpu can do the enqueuing at the same time, so I am
proposing to use Jason's proposal to enable multi cpus to do
concurrent enqueuing without taking any lock.
>
>>
>> For enqueuing, multiple consumers is protected by producer_lock, see
>> pfifo_fast_enqueue() -> skb_array_produce() -> ptr_ring_produce().
>
> I think you seriously misunderstand how we classify MPMC or MPSC,
> it is not about how we lock them, it is about whether we truly have
> a single or multiple consumers regardless of locks used, because the
> goal is to go lockless.
I think I am only relying on the MPSC(multi-produce & single-consumer),
as explained above.
>
>> I am not sure if lockless MSPC can work with the process context, but
>> even if not, the enqueuing is also protected by rcu_read_lock_bh(),
>> which provides some kind of atomicity, so that producer_lock can be
>> reomved when lockless MSPC is used.
>
>
> Not sure if I can even understand what you are saying here, Jason's
> code only disables preemption with busy wait, I can't see why it can
> not be used in the process context.
I am saying q->enqeue() is protected by rcu_read_lock_bh().
rcu_read_lock_bh() will disable preemption for us for most configuation,
otherwise it will break netdev_xmit_more() interface too, for it relies
on the cpu not being prempted by using per cpu var(softnet_data.xmit.more).
>
> Thanks.
>
> .
>
next prev parent reply other threads:[~2021-03-24 2:37 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-13 2:47 [PATCH RFC] net: sched: implement TCQ_F_CAN_BYPASS for lockless qdisc Yunsheng Lin
2021-03-14 0:03 ` Vladimir Oltean
2021-03-14 10:15 ` Marc Kleine-Budde
2021-03-15 0:50 ` Yunsheng Lin
2021-03-15 3:10 ` [RFC v2] " Yunsheng Lin
2021-03-15 12:29 ` Vladimir Oltean
2021-03-15 13:09 ` Marc Kleine-Budde
2021-03-15 18:53 ` Jakub Kicinski
2021-03-16 0:35 ` Yunsheng Lin
2021-03-16 3:47 ` [Linuxarm] " Yunsheng Lin
2021-03-16 8:15 ` Eric Dumazet
2021-03-16 12:36 ` Yunsheng Lin
2021-03-16 22:48 ` Cong Wang
2021-03-17 1:14 ` Yunsheng Lin
2021-03-17 13:35 ` Toke Høiland-Jørgensen
2021-03-17 13:45 ` Jason A. Donenfeld
2021-03-18 7:33 ` [Linuxarm] " Yunsheng Lin
2021-03-19 18:15 ` Cong Wang
2021-03-22 0:55 ` Yunsheng Lin
2021-03-24 1:49 ` Cong Wang
2021-03-24 2:36 ` Yunsheng Lin [this message]
2021-03-19 19:03 ` Jason A. Donenfeld
2021-03-22 1:05 ` Yunsheng Lin
2021-03-18 7:10 ` Ahmad Fatoum
2021-03-18 7:46 ` Yunsheng Lin
2021-03-18 9:09 ` Ahmad Fatoum
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=750de5f8-ff1a-a300-e5b5-8381893e2db9@huawei.com \
--to=linyunsheng@huawei.com \
--cc=Jason@zx2c4.com \
--cc=andriin@fb.com \
--cc=ap420073@gmail.com \
--cc=ast@kernel.org \
--cc=cong.wang@bytedance.com \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=kuba@kernel.org \
--cc=linux-can@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxarm@openeuler.org \
--cc=mkl@pengutronix.de \
--cc=netdev@vger.kernel.org \
--cc=olteanv@gmail.com \
--cc=toke@redhat.com \
--cc=weiwan@google.com \
--cc=xiyou.wangcong@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;
as well as URLs for NNTP newsgroup(s).