netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "D. Wythe" <alibuda@linux.alibaba.com>
To: kgraul@linux.ibm.com
Cc: kuba@kernel.org, davem@davemloft.net, netdev@vger.kernel.org,
	linux-s390@vger.kernel.org, linux-rdma@vger.kernel.org,
	"D. Wythe" <alibuda@linux.alibaba.com>
Subject: [PATCH net-next 0/3]  Optimizing performance in short-lived
Date: Thu, 27 Jan 2022 20:08:00 +0800	[thread overview]
Message-ID: <cover.1643284658.git.alibuda@linux.alibaba.com> (raw)

From: "D. Wythe" <alibuda@linux.alibaba.com>

This patch set aims to optimizing performance of SMC in short-lived
links scenarios, which is quite unsatisfactory right now.

In our benchmark, we test it with follow scripts:

./wrk -c 10000 -t 4 -H 'Connection: Close' -d 20 http://smc-server

Current performance figures like that:

Running 20s test @ http://11.213.45.6
  4 threads and 10000 connections
  4956 requests in 20.06s, 3.24MB read
  Socket errors: connect 0, read 0, write 672, timeout 0
Requests/sec:    247.07
Transfer/sec:    165.28KB

There are many reasons for this phenomenon, this patch set doesn't
solve it all though, but it can be well alleviated with it in.

Patch 1/3  (Make smc_tcp_listen_work() independent) :

Separate smc_tcp_listen_work() from smc_listen_work(), make them
independent of each other, the busy SMC handshake can not affect new TCP
connections visit any more. Avoid discarding a large number of TCP
connections after being overstock, which is undoubtedly raise the
connection establishment time.

Patch 2/3 (Limits SMC backlog connections):

Since patch 1 has separated smc_tcp_listen_work() from
smc_listen_work(), an unrestricted TCP accept have come into being. This
patch try to put a limit on SMC backlog connections refers to
implementation of TCP.

Patch 3/3 (Fallback when SMC handshake workqueue congested):

Considering the complexity of SMC handshake right now, in short-lived
links scenarios, this may not be the main scenario of SMC though, it's
performance is still quite poor. This Patch try to provide auto fallback
case when SMC handshake workqueue congested, which is the sign of SMC
handshake stacking in our opinion.

Of course, it's optional.

After this patch set, performance figures like that:

Running 20s test @ http://11.213.45.6
  4 threads and 10000 connections
  693253 requests in 20.10s, 452.88MB read
Requests/sec:  34488.13
Transfer/sec:     22.53MB

That's a quite well performance improvement, about to 6 to 7 times in my
environment.

D. Wythe (3):
  net/smc: Make smc_tcp_listen_work() independent
  net/smc: Limits backlog connections
  net/smc: Fallback when SMC handshake workqueue

 include/linux/tcp.h  |  1 +
 net/ipv4/tcp_input.c |  3 +-
 net/smc/Kconfig      | 12 ++++++++
 net/smc/af_smc.c     | 78 ++++++++++++++++++++++++++++++++++++++++++++++++++--
 net/smc/smc.h        |  5 ++++
 5 files changed, 96 insertions(+), 3 deletions(-)

-- 
1.8.3.1


             reply	other threads:[~2022-01-27 12:08 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-27 12:08 D. Wythe [this message]
2022-01-27 12:08 ` [PATCH net-next 1/3] net/smc: Make smc_tcp_listen_work() independent D. Wythe
2022-01-27 12:08 ` [PATCH net-next 2/3] net/smc: Limits backlog connections D. Wythe
2022-01-27 15:52   ` kernel test robot
2022-01-27 15:52   ` kernel test robot
2022-01-27 23:23   ` kernel test robot
2022-01-27 12:08 ` [PATCH net-next 3/3] net/smc: Fallback when handshake workqueue congested D. Wythe
2022-01-27 17:09   ` Matthieu Baerts
2022-01-28 13:54     ` D. Wythe
2022-01-28 14:05     ` D. Wythe
2022-01-28  7:17   ` Tony Lu

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=cover.1643284658.git.alibuda@linux.alibaba.com \
    --to=alibuda@linux.alibaba.com \
    --cc=davem@davemloft.net \
    --cc=kgraul@linux.ibm.com \
    --cc=kuba@kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    /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).