From: Yunsheng Lin <linyunsheng@huawei.com>
To: Marc Kleine-Budde <mkl@pengutronix.de>,
Vladimir Oltean <olteanv@gmail.com>
Cc: <davem@davemloft.net>, <kuba@kernel.org>, <ast@kernel.org>,
<daniel@iogearbox.net>, <andriin@fb.com>, <edumazet@google.com>,
<weiwan@google.com>, <cong.wang@bytedance.com>,
<ap420073@gmail.com>, <netdev@vger.kernel.org>,
<linux-kernel@vger.kernel.org>, <linuxarm@openeuler.org>,
<pabeni@redhat.com>, linux-can <linux-can@vger.kernel.org>
Subject: Re: [PATCH RFC] net: sched: implement TCQ_F_CAN_BYPASS for lockless qdisc
Date: Mon, 15 Mar 2021 08:50:00 +0800 [thread overview]
Message-ID: <3e6ecce5-188e-d2cf-69e4-ddb672236c27@huawei.com> (raw)
In-Reply-To: <298228b3-af1d-6907-92a3-b273dad7a150@pengutronix.de>
On 2021/3/14 18:15, Marc Kleine-Budde wrote:
> Cc += linux-can@vger.kernel.org
>
> On 3/14/21 1:03 AM, Vladimir Oltean wrote:
>> On Sat, Mar 13, 2021 at 10:47:47AM +0800, Yunsheng Lin wrote:
>>> Currently pfifo_fast has both TCQ_F_CAN_BYPASS and TCQ_F_NOLOCK
>>> flag set, but queue discipline by-pass does not work for lockless
>>> qdisc because skb is always enqueued to qdisc even when the qdisc
>>> is empty, see __dev_xmit_skb().
>>>
>>> This patch calles sch_direct_xmit() to transmit the skb directly
>>> to the driver for empty lockless qdisc too, which aviod enqueuing
>>> and dequeuing operation. qdisc->empty is set to false whenever a
>>> skb is enqueued, and is set to true when skb dequeuing return NULL,
>>> see pfifo_fast_dequeue().
>>>
>>> Also, qdisc is scheduled at the end of qdisc_run_end() when q->empty
>>> is false to avoid packet stuck problem.
>>>
>>> The performance for ip_forward test increases about 10% with this
>>> patch.
>>>
>>> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
>>> ---
>>
>> I can confirm the ~10% IP forwarding throughput improvement brought by
>> this patch, but as you might be aware, there was a previous attempt to
>> add qdisc bypass to pfifo_fast by Paolo Abeni:
>> https://lore.kernel.org/netdev/661cc33a-5f65-2769-cc1a-65791cb4b131@pengutronix.de/
Thanks for mention the previous attempt to add qdisc bypass to pfifo_fast.
>> It was reverted because TX reordering was observed with SocketCAN
>> (although, presumably it should also be seen with Ethernet and such).
When writing this patch, I was more foucusing on packet stuck problem
when TCQ_F_CAN_BYPASS is added for lockless qdisc.
When I am looking at flexcan_start_xmit() used by the can driver you mentioned,
it calls netif_stop_queue() to disable the queue when sending each skb, which may
cuause other skb to be requeued, see dev_requeue_skb() called by sch_direct_xmit(),
and q->empty is still true when this happens, so other cpu may send skb directly
bypassing the requeued skb, causing an out of order problem.
I will try to deal with the above requeued skb problem, and see if there are other
timing issus beside the requeued skb problem.
Thanks for the testing again.
>
> Thanks for testing that, I just stumbled over this patch by accident.
>
> Marc
>
next prev parent reply other threads:[~2021-03-15 0:51 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <1615603667-22568-1-git-send-email-linyunsheng@huawei.com>
[not found] ` <20210314000350.2mrhvprsi77qwqdi@skbuf>
2021-03-14 10:15 ` [PATCH RFC] net: sched: implement TCQ_F_CAN_BYPASS for lockless qdisc Marc Kleine-Budde
2021-03-15 0:50 ` Yunsheng Lin [this message]
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
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=3e6ecce5-188e-d2cf-69e4-ddb672236c27@huawei.com \
--to=linyunsheng@huawei.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=pabeni@redhat.com \
--cc=weiwan@google.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).