[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1446233450.6254.29.camel@edumazet-glaptop2.roam.corp.google.com>
Date: Fri, 30 Oct 2015 12:30:50 -0700
From: Eric Dumazet <eric.dumazet@...il.com>
To: Cong Wang <xiyou.wangcong@...il.com>
Cc: netdev@...r.kernel.org, Jamal Hadi Salim <jhs@...atatu.com>
Subject: Re: [Patch net-next v2 2/4] net_sched: update hierarchical backlog
too
On Fri, 2015-10-30 at 11:22 -0700, Cong Wang wrote:
> When the bottom qdisc decides to, for example, drop some packet,
> it calls qdisc_tree_decrease_qlen() to update the queue length
> for all its ancestors, we need to update the backlog too to
> keep the stats on root qdisc accurate.
>
> Cc: Jamal Hadi Salim <jhs@...atatu.com>
> Acked-by: Jamal Hadi Salim <jhs@...atatu.com>
> Signed-off-by: Cong Wang <xiyou.wangcong@...il.com>
...
>
> diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
> index 3abab53..498f0a2 100644
> --- a/net/sched/sch_sfq.c
> +++ b/net/sched/sch_sfq.c
> @@ -346,7 +346,7 @@ static int
> sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
> {
> struct sfq_sched_data *q = qdisc_priv(sch);
> - unsigned int hash;
> + unsigned int hash, dropped;
> sfq_index x, qlen;
> struct sfq_slot *slot;
> int uninitialized_var(ret);
> @@ -461,7 +461,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
> return NET_XMIT_SUCCESS;
>
> qlen = slot->qlen;
> - sfq_drop(sch);
> + dropped = sfq_drop(sch);
> /* Return Congestion Notification only if we dropped a packet
> * from this flow.
> */
> @@ -469,7 +469,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
> return NET_XMIT_CN;
I believe you missed the NET_XMIT_CN cases.
SFQ can drop a prior packet, and queue current packet.
qdisc_tree_reduce_backlog() wont be called to update parents.
Not sure about other qdisc(s)
--
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
Powered by blists - more mailing lists