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

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: <1423051045.907.108.camel@edumazet-glaptop2.roam.corp.google.com>
Date:	Wed, 04 Feb 2015 03:57:25 -0800
From:	Eric Dumazet <eric.dumazet@...il.com>
To:	Michal Kazior <michal.kazior@...to.com>
Cc:	linux-wireless <linux-wireless@...r.kernel.org>,
	Network Development <netdev@...r.kernel.org>,
	eyalpe@....mellanox.co.il
Subject: Re: Throughput regression with `tcp: refine TSO autosizing`

On Wed, 2015-02-04 at 12:35 +0100, Michal Kazior wrote:

> > (Or maybe wifi drivers should start to use skb->xmit_more as a signal to end aggregation)
> 
> This could work if your firmware/device supports this kind of thing.
> To my understanding ath10k firmware doesn't.

This is a pure software signal. You do not need firmware support.

Idea is the following :

Your driver gets a train of messages, coming from upper layers (TCP, IP,
qdisc)

It can know that a packet is not the last one, by looking at
skb->xmit_more.

Basically, aggregation logic could use this signal as a very clear
indicator you got the end of a train -> force the xmit right now.

To disable gso you would have to use :

ethtool -K wlan1 gso off



--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html