From fd245a4adb5288eac37250875f237c40a20a1944 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 20 Jan 2011 05:27:16 +0000 Subject: net_sched: move TCQ_F_THROTTLED flag In commit 371121057607e (net: QDISC_STATE_RUNNING dont need atomic bit ops) I moved QDISC_STATE_RUNNING flag to __state container, located in the cache line containing qdisc lock and often dirtied fields. I now move TCQ_F_THROTTLED bit too, so that we let first cache line read mostly, and shared by all cpus. This should speedup HTB/CBQ for example. Not using test_bit()/__clear_bit()/__test_and_set_bit allows to use an "unsigned int" for __state container, reducing by 8 bytes Qdisc size. Introduce helpers to hide implementation details. Signed-off-by: Eric Dumazet CC: Patrick McHardy CC: Jesper Dangaard Brouer CC: Jarek Poplawski CC: Jamal Hadi Salim CC: Stephen Hemminger Signed-off-by: David S. Miller --- net/sched/sch_netem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/sched/sch_netem.c') diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index c2bbbe60d54..c26ef3614f7 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -266,7 +266,7 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch) struct netem_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; - if (sch->flags & TCQ_F_THROTTLED) + if (qdisc_is_throttled(sch)) return NULL; skb = q->qdisc->ops->peek(q->qdisc); -- cgit v1.2.3