From: Kai <KaiShen@linux.alibaba.com>
To: Paolo Abeni <pabeni@redhat.com>,
kgraul@linux.ibm.com, wenjia@linux.ibm.com, jaka@linux.ibm.com,
kuba@kernel.org, davem@davemloft.net, dsahern@kernel.org
Cc: netdev@vger.kernel.org, linux-s390@vger.kernel.org,
linux-rdma@vger.kernel.org
Subject: Re: [PATCH net-next] net/smc: introduce shadow sockets for fallback connections
Date: Fri, 24 Mar 2023 16:21:48 +0800 [thread overview]
Message-ID: <c7434855-b569-4e10-fd19-7f7d525cad7f@linux.alibaba.com> (raw)
In-Reply-To: <8f4bd9333117eda4c5ff324f92b969d9a6b57b65.camel@redhat.com>
On 3/22/23 9:08 PM, Paolo Abeni wrote:
>
> It looks like only the shadow sockets' receive queue is needed/used.
>
> Have you considered instead adding 2 receive queues to smc_sock, and
> implement a custom accept() variant fetching the accepted sockets from
> there?
>
> That will allow better encapsulating the changes into the smc code and
> will avoid creating that 2 non-listening but almost listening sockets
> which look quite strange.
>
> Cheers,
>
> Paolo
I am not so sure about this two sockets implementation but Here are my
concerns:
1. When I tried to implement a custom accept, I found the function.
mem_cgroup_charge_skmem is not exported and SMC-R couldn't access it as
a module. If there are more functions like this in future updates this
could be a problem.
3. The custom accept should synchronize with future updates of TCP
accept.
2. SMC-R is trying to behave like TCP and if we implement custom accept,
there may be repeated code and looks not good.
Thanks,
Kai
next prev parent reply other threads:[~2023-03-24 8:22 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-21 7:19 [PATCH net-next] net/smc: introduce shadow sockets for fallback connections Kai Shen
2023-03-22 13:08 ` Paolo Abeni
2023-03-24 8:21 ` Kai [this message]
2023-03-22 17:09 ` Wenjia Zhang
2023-03-24 7:26 ` Kai
2023-03-29 9:41 ` Wenjia Zhang
2023-04-03 10:18 ` Kai
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=c7434855-b569-4e10-fd19-7f7d525cad7f@linux.alibaba.com \
--to=kaishen@linux.alibaba.com \
--cc=davem@davemloft.net \
--cc=dsahern@kernel.org \
--cc=jaka@linux.ibm.com \
--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 \
--cc=pabeni@redhat.com \
--cc=wenjia@linux.ibm.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