Re: [RFC net-next 4/4] tcp: defer regular ACK while processing socket backlog

On Thu, Sep 7, 2023 at 6:50 PM Dave Taht [off-list ref] wrote:

When you once said you were going to find a way to reduce the number of acks, I did not expect this.
Has this been tested on arm or at lower rates, such as a gigabit? Or against WiFi?

Not yet, but my guess is that it could benefit wifi drivers that are
not using GRO,
particularly if the TCP payload is in skb->head instead of a page fragment,
defeating tcp_try_coalesce() ability to 'pretend GRO was there in the
first place'.

I sent an RFC so that others could perform tests ;)

Regardless:

Acked-by: Dave Taht <redacted>

--
Oct 30: https://netdevconf.info/0x17/news/the-maestro-and-the-music-bof.html
Dave Täht CSO, LibreQos