Re: Throughput regression with `tcp: refine TSO autosizing`

On Fri, 2015-02-06 at 14:31 +0000, David Laight wrote:

From: Eric Dumazet

quoted

On Fri, 2015-02-06 at 05:53 -0800, Eric Dumazet wrote:

quoted

wifi could eventually do that, providing in skb->tx_completion_delay_us
the time spent in wifi driver.

This way, we would have no penalty for network devices doing normal skb
orphaning (loopback interface, ethernet, ...)

Another way would be that wifi does an automatic orphaning after 1 or
2ms.

Couldn't you do byte counting?
So orphan enough packets to keep a few ms of tx traffic (at the current
tx rate) orphaned.
You might need to give the hardware both orphaned and non-orphaned (parented?)
packets and orphan some when you get a tx complete for an orphaned packet.

We already have byte counting.

The thing is : A driver can keep an skb for itself, but calling
skb_orphan() in time to allow a socket to send more packets.

For say a UDP server, it would be quite mandatory, as it usually uses a
single UDP socket to receive and send messages.