From: Jakub Kicinski <kuba@kernel.org>
To: liqiang <liqiang64@huawei.com>
Cc: <wenjia@linux.ibm.com>, <jaka@linux.ibm.com>,
<alibuda@linux.alibaba.com>, <tonylu@linux.alibaba.com>,
<guwen@linux.alibaba.com>, <dust.li@linux.alibaba.com>,
<linux-s390@vger.kernel.org>, <netdev@vger.kernel.org>,
<linux-kernel@vger.kernel.org>, <luanjianhai@huawei.com>,
<zhangxuzhou4@huawei.com>, <dengguangxing@huawei.com>,
<gaochao24@huawei.com>
Subject: Re: [PATCH net-next v3] net/smc: Optimize the search method of reused buf_desc
Date: Mon, 18 Nov 2024 18:21:41 -0800 [thread overview]
Message-ID: <20241118182141.20471ab8@kernel.org> (raw)
In-Reply-To: <20241112092216.1439-1-liqiang64@huawei.com>
On Tue, 12 Nov 2024 17:22:16 +0800 liqiang wrote:
> We create a lock-less link list for the currently
> idle reusable smc_buf_desc.
>
> When the 'used' filed mark to 0, it is added to
> the lock-less linked list.
>
> When a new connection is established, a suitable
> element is obtained directly, which eliminates the
> need for traversal and search, and does not require
> locking resource.
>
> Through my testing, this patch can significantly improve
> the link establishment speed of SMC, especially in the
> multi-threaded short connection benchmark.
>
> I tested the time-consuming comparison of this function
> under multiple connections based on redis-benchmark
> (test in smc loopback-ism mode):
>
> The function 'smc_buf_get_slot' takes less time when a
> new SMC link is established:
> 1. 5us->100ns (when there are 200 active links);
> 2. 30us->100ns (when there are 1000 active links).
We're closing net-next and didn't get any review tags on this patch,
either from IBM or Alibaba folks. Please try again after the merge
window (after Dec 2nd, once v6.13-rc1 is tagged).
--
pw-bot: defer
prev parent reply other threads:[~2024-11-19 2:21 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-01 8:23 [PATCH net-next] net/smc: Optimize the search method of reused buf_desc liqiang
2024-11-01 10:52 ` Dust Li
2024-11-02 6:43 ` Li Qiang
2024-11-04 8:13 ` Dust Li
2024-11-04 8:47 ` Li Qiang
2024-11-05 3:19 ` [PATCH v2 " liqiang
2024-11-05 14:44 ` Dust Li
2024-11-06 7:05 ` Li Qiang
2024-11-12 9:22 ` [PATCH net-next v3] " liqiang
2024-11-19 2:21 ` Jakub Kicinski [this message]
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=20241118182141.20471ab8@kernel.org \
--to=kuba@kernel.org \
--cc=alibuda@linux.alibaba.com \
--cc=dengguangxing@huawei.com \
--cc=dust.li@linux.alibaba.com \
--cc=gaochao24@huawei.com \
--cc=guwen@linux.alibaba.com \
--cc=jaka@linux.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-s390@vger.kernel.org \
--cc=liqiang64@huawei.com \
--cc=luanjianhai@huawei.com \
--cc=netdev@vger.kernel.org \
--cc=tonylu@linux.alibaba.com \
--cc=wenjia@linux.ibm.com \
--cc=zhangxuzhou4@huawei.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).