netdev - Re: [PATCH net 1/4] Revert "net/smc: don't wait for send buffer space when data was already sent"

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <8445f69e-54e6-0c54-a2de-0560cbf0e6ce@linux.ibm.com>
Date:   Sat, 6 Nov 2021 13:46:00 +0100
From:   Karsten Graul <kgraul@...ux.ibm.com>
To:     Tony Lu <tonylu@...ux.alibaba.com>
Cc:     Jakub Kicinski <kuba@...nel.org>, davem@...emloft.net,
        netdev@...r.kernel.org, linux-s390@...r.kernel.org,
        linux-rdma@...r.kernel.org, jacob.qi@...ux.alibaba.com,
        xuanzhuo@...ux.alibaba.com, guwen@...ux.alibaba.com,
        dust.li@...ux.alibaba.com
Subject: Re: [PATCH net 1/4] Revert "net/smc: don't wait for send buffer space
 when data was already sent"

On 03/11/2021 04:06, Tony Lu wrote:
> 
> I agree with you. I am curious about this deadlock scene. If it was
> convenient, could you provide a reproducible test case? We are also
> setting up a SMC CI/CD system to find the compatible and performance
> fallback problems. Maybe we could do something to make it better.

Run an echo server that uses blocking sockets. First call recv() with an 1MB buffer
and when recv() returns then send all received bytes back to the client, no matter
how many bytes where received. Run this in a loop (recv / send).
On the client side also use only blocking sockets and a send / recv loop. Use
an 1MB data buffer and call send() with the whole 1MB of data.
Now run that with both scenarios (send() returns lesser bytes than requested vs. not).