[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1465407776.7945.24.camel@edumazet-glaptop3.roam.corp.google.com>
Date: Wed, 08 Jun 2016 10:42:56 -0700
From: Eric Dumazet <eric.dumazet@...il.com>
To: Florian Westphal <fw@...len.de>
Cc: netdev@...r.kernel.org
Subject: Re: [PATCH -next 3/4] sched: remove qdisc_rehape_fail
On Wed, 2016-06-08 at 17:35 +0200, Florian Westphal wrote:
> After the removal of TCA_CBQ_POLICE in cbq scheduler qdisc->reshape_fail
> is always NULL, i.e. qdisc_rehape_fail is now the same as qdisc_drop.
>
> Signed-off-by: Florian Westphal <fw@...len.de>
> ---
> include/net/sch_generic.h | 19 -------------------
> net/sched/sch_fifo.c | 4 ++--
> net/sched/sch_netem.c | 4 ++--
> net/sched/sch_plug.c | 2 +-
> net/sched/sch_tbf.c | 4 ++--
> 5 files changed, 7 insertions(+), 26 deletions(-)
>
> diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
> index c069ac1..a9aec63 100644
> --- a/include/net/sch_generic.h
> +++ b/include/net/sch_generic.h
> @@ -63,9 +63,6 @@ struct Qdisc {
> struct list_head list;
> u32 handle;
> u32 parent;
> - int (*reshape_fail)(struct sk_buff *skb,
> - struct Qdisc *q);
> -
> void *u32_node;
>
You removed 2 pointers from Qdisc, so now next_sched & gso_skb are in a
different cache line than ->state
Some performance penalty is expected, unless you move a read_mostly
field there to compensate.
Powered by blists - more mailing lists