diff options
| author | Eric Dumazet <edumazet@google.com> | 2016-06-22 09:16:49 +0300 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2016-06-25 19:19:35 +0300 |
| commit | 520ac30f45519b0a82dd92117c181d1d6144677b (patch) | |
| tree | a3189ae1ab3b5be6213716e42ddaec082578e774 /net/sched/sch_prio.c | |
| parent | 36195d869e4b1dbf81bafa3a31bb095a3c013bdd (diff) | |
| download | linux-520ac30f45519b0a82dd92117c181d1d6144677b.tar.xz | |
net_sched: drop packets after root qdisc lock is released
Qdisc performance suffers when packets are dropped at enqueue()
time because drops (kfree_skb()) are done while qdisc lock is held,
delaying a dequeue() draining the queue.
Nominal throughput can be reduced by 50 % when this happens,
at a time we would like the dequeue() to proceed as fast as possible.
Even FQ is vulnerable to this problem, while one of FQ goals was
to provide some flow isolation.
This patch adds a 'struct sk_buff **to_free' parameter to all
qdisc->enqueue(), and in qdisc_drop() helper.
I measured a performance increase of up to 12 %, but this patch
is a prereq so that future batches in enqueue() can fly.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/sched/sch_prio.c')
| -rw-r--r-- | net/sched/sch_prio.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index de492682caee..f4d443aeae54 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -67,7 +67,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) } static int -prio_enqueue(struct sk_buff *skb, struct Qdisc *sch) +prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct Qdisc *qdisc; int ret; @@ -83,7 +83,7 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch) } #endif - ret = qdisc_enqueue(skb, qdisc); + ret = qdisc_enqueue(skb, qdisc, to_free); if (ret == NET_XMIT_SUCCESS) { qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; |