From 28cff537ef2eed9307bc7e4e40745075637bec56 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 22 Mar 2019 16:01:55 +0100 Subject: net: sched: add empty status flag for NOLOCK qdisc The queue is marked not empty after acquiring the seqlock, and it's up to the NOLOCK qdisc clearing such flag on dequeue. Since the empty status lays on the same cache-line of the seqlock, it's always hot on cache during the updates. This makes the empty flag update a little bit loosy. Given the lack of synchronization between enqueue and dequeue, this is unavoidable. v2 -> v3: - qdisc_is_empty() has a const argument (Eric) v1 -> v2: - use really an 'empty' flag instead of 'not_empty', as suggested by Eric Signed-off-by: Paolo Abeni Reviewed-by: Eric Dumazet Reviewed-by: Ivan Vecera Signed-off-by: David S. Miller --- net/sched/sch_generic.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net') diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index a117d9260558..81356ef38d1d 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -671,6 +671,8 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) qdisc_qstats_cpu_backlog_dec(qdisc, skb); qdisc_bstats_cpu_update(qdisc, skb); qdisc_qstats_atomic_qlen_dec(qdisc); + } else { + qdisc->empty = true; } return skb; @@ -880,6 +882,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; + sch->empty = true; dev_hold(dev); refcount_set(&sch->refcnt, 1); -- cgit From ba27b4cdaaa66561aaedb2101876e563738d36fe Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 22 Mar 2019 16:01:56 +0100 Subject: net: dev: introduce support for sch BYPASS for lockless qdisc With commit c5ad119fb6c0 ("net: sched: pfifo_fast use skb_array") pfifo_fast no longer benefit from the TCQ_F_CAN_BYPASS optimization. Due to retpolines the cost of the enqueue()/dequeue() pair has become relevant and we observe measurable regression for the uncontended scenario when the packet-rate is below line rate. After commit 46b1c18f9deb ("net: sched: put back q.qlen into a single location") we can check for empty qdisc with a reasonably fast operation even for nolock qdiscs. This change extends TCQ_F_CAN_BYPASS support to nolock qdisc. The new chunk of code mirrors closely the existing one for traditional qdisc, leveraging a newly introduced helper to read atomically the qdisc length. Tested with pktgen in queue xmit mode, with pfifo_fast, a MQ device, and MQ root qdisc: threads vanilla patched kpps kpps 1 2465 2889 2 4304 5188 4 7898 9589 Same as above, but with a single queue device: threads vanilla patched kpps kpps 1 2556 2827 2 2900 2900 4 5000 5000 8 4700 4700 No mesaurable changes in the contended scenarios, and more 10% improvement in the uncontended ones. v1 -> v2: - rebased after flag name change Signed-off-by: Paolo Abeni Tested-by: Ivan Vecera Reviewed-by: Eric Dumazet Reviewed-by: Ivan Vecera Signed-off-by: David S. Miller --- net/core/dev.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'net') diff --git a/net/core/dev.c b/net/core/dev.c index 357111431ec9..676c9418f8e4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3468,6 +3468,15 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { __qdisc_drop(skb, &to_free); rc = NET_XMIT_DROP; + } else if ((q->flags & TCQ_F_CAN_BYPASS) && q->empty && + qdisc_run_begin(q)) { + qdisc_bstats_cpu_update(q, skb); + + if (sch_direct_xmit(skb, q, dev, txq, NULL, true)) + __qdisc_run(q); + + qdisc_run_end(q); + rc = NET_XMIT_SUCCESS; } else { rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; qdisc_run(q); -- cgit