[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87v8pgv0f1.fsf@toke.dk>
Date: Thu, 22 Sep 2022 00:16:02 +0200
From: Toke Høiland-Jørgensen <toke@...hat.com>
To: Jesper Dangaard Brouer <brouer@...hat.com>,
Ilias Apalodimas <ilias.apalodimas@...aro.org>,
netdev@...r.kernel.org
Cc: bpf@...r.kernel.org, Lorenzo Bianconi <lorenzo@...nel.org>,
mtahhan@...hat.com, mcroce@...rosoft.com
Subject: Re: [PATCH net-next] xdp: improve page_pool xdp_return performance
Jesper Dangaard Brouer <brouer@...hat.com> writes:
> During LPC2022 I meetup with my page_pool co-maintainer Ilias. When
> discussing page_pool code we realised/remembered certain optimizations
> had not been fully utilised.
>
> Since commit c07aea3ef4d4 ("mm: add a signature in struct page") struct
> page have a direct pointer to the page_pool object this page was
> allocated from.
>
> Thus, with this info it is possible to skip the rhashtable_lookup to
> find the page_pool object in __xdp_return().
>
> The rcu_read_lock can be removed as it was tied to xdp_mem_allocator.
> The page_pool object is still safe to access as it tracks inflight pages
> and (potentially) schedules final release from a work queue.
>
> Created a micro benchmark of XDP redirecting from mlx5 into veth with
> XDP_DROP bpf-prog on the peer veth device. This increased performance
> 6.5% from approx 8.45Mpps to 9Mpps corresponding to using 7 nanosec
> (27 cycles at 3.8GHz) less per packet.
>
> Suggested-by: Ilias Apalodimas <ilias.apalodimas@...aro.org>
> Signed-off-by: Jesper Dangaard Brouer <brouer@...hat.com>
Nice! The two of you should get together in person more often ;)
Acked-by: Toke Høiland-Jørgensen <toke@...hat.com>
Powered by blists - more mailing lists