[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87bksgv26h.fsf@toke.dk>
Date: Fri, 19 Aug 2022 14:38:14 +0200
From: Toke Høiland-Jørgensen <toke@...hat.com>
To: Jakub Kicinski <kuba@...nel.org>
Cc: "David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Paolo Abeni <pabeni@...hat.com>, netdev@...r.kernel.org,
bpf@...r.kernel.org
Subject: Re: [PATCH bpf-next 1/3] dev: Move received_rps counter next to RPS
members in softnet data
Jakub Kicinski <kuba@...nel.org> writes:
> On Thu, 18 Aug 2022 18:59:03 +0200 Toke Høiland-Jørgensen wrote:
>> Move the received_rps counter value next to the other RPS-related members
>> in softnet_data. This closes two four-byte holes in the structure, making
>> room for another pointer in the first two cache lines without bumping the
>> xmit struct to its own line.
>
> What's the pointer you're making space for (which I hope will explain
> why this patch is part of this otherwise bpf series)?
The XDP queueing series adds a pointer to keep track of which interfaces
were scheduled for transmission using the XDP dequeue hook (similar to
how the qdisc wake code works):
https://lore.kernel.org/r/20220713111430.134810-12-toke@redhat.com
Note that it's still up in the air if this ends up being the way this
will be implemented, so I'm OK with dropping this patch for now if you'd
rather wait until it's really needed. OTOH it also seemed like a benign
change on its own, so I figured I might as well include this patch when
sending these out. WDYT?
-Toke
Powered by blists - more mailing lists