[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <1484933515.16328.139.camel@edumazet-glaptop3.roam.corp.google.com>
Date: Fri, 20 Jan 2017 09:31:55 -0800
From: Eric Dumazet <eric.dumazet@...il.com>
To: Tom Herbert <tom@...bertland.com>
Cc: Andrew Collins <acollins@...dlepoint.com>,
Linux Kernel Network Developers <netdev@...r.kernel.org>
Subject: Re: [PATCH net-next] fq_codel: Avoid regenerating skb flow hash
unless necessary
On Fri, 2017-01-20 at 09:23 -0800, Tom Herbert wrote:
> So the perturbing of the hash is no longer needed for fq_codel?
Right, we never implemented a timer to change the perturbation anyway.
Note that local TCP flows now implement their own hash change when
needed.
Powered by blists - more mailing lists