netdev - Re: [PATCH net-next] tcp: try to defer / return acked skbs to originating CPU

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: <20260117091010.3133de3b@kernel.org>
Date: Sat, 17 Jan 2026 09:10:10 -0800
From: Jakub Kicinski <kuba@...nel.org>
To: edumazet@...gle.com
Cc: kuniyu@...gle.com, ncardwell@...gle.com, netdev@...r.kernel.org,
 davem@...emloft.net, pabeni@...hat.com, andrew+netdev@...n.ch,
 horms@...nel.org
Subject: Re: [PATCH net-next] tcp: try to defer / return acked skbs to
 originating CPU

On Sat, 17 Jan 2026 08:42:55 -0800 Jakub Kicinski wrote:
> Running a memcache-like workload under production(ish) load
> on a 300 thread AMD machine we see ~3% of CPU time spent
> in kmem_cache_free() via tcp_ack(), freeing skbs from rtx queue.
> This workloads pins workers away from softirq CPU so
> the Tx skbs are pretty much always allocated on a different
> CPU than where the ACKs arrive. Try to use the defer skb free
> queue to return the skbs back to where they came from.
> This results in a ~4% performance improvement for the workload.

In the interest of full transparency the performance testing was
done on a 6.13-ish kernel. But I don't see anything that'd make
the situation better upstream..