summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorJesper Dangaard Brouer <brouer@redhat.com>2014-10-01 22:35:59 +0200
committerDavid S. Miller <davem@davemloft.net>2014-10-03 12:37:06 -0700
commit5772e9a3463b264cee5a4e73ef586ad482d7ba48 (patch)
treeed566860e5e0a567d9ea22d22ede3eaf8a55bcd5 /net
parent38df6492eb511d2a6823303cb1a194c4fe423154 (diff)
downloadop-kernel-dev-5772e9a3463b264cee5a4e73ef586ad482d7ba48.zip
op-kernel-dev-5772e9a3463b264cee5a4e73ef586ad482d7ba48.tar.gz
qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE
Based on DaveM's recent API work on dev_hard_start_xmit(), that allows sending/processing an entire skb list. This patch implements qdisc bulk dequeue, by allowing multiple packets to be dequeued in dequeue_skb(). The optimization principle for this is two fold, (1) to amortize locking cost and (2) avoid expensive tailptr update for notifying HW. (1) Several packets are dequeued while holding the qdisc root_lock, amortizing locking cost over several packet. The dequeued SKB list is processed under the TXQ lock in dev_hard_start_xmit(), thus also amortizing the cost of the TXQ lock. (2) Further more, dev_hard_start_xmit() will utilize the skb->xmit_more API to delay HW tailptr update, which also reduces the cost per packet. One restriction of the new API is that every SKB must belong to the same TXQ. This patch takes the easy way out, by restricting bulk dequeue to qdisc's with the TCQ_F_ONETXQUEUE flag, that specifies the qdisc only have attached a single TXQ. Some detail about the flow; dev_hard_start_xmit() will process the skb list, and transmit packets individually towards the driver (see xmit_one()). In case the driver stops midway in the list, the remaining skb list is returned by dev_hard_start_xmit(). In sch_direct_xmit() this returned list is requeued by dev_requeue_skb(). To avoid overshooting the HW limits, which results in requeuing, the patch limits the amount of bytes dequeued, based on the drivers BQL limits. In-effect bulking will only happen for BQL enabled drivers. Small amounts for extra HoL blocking (2x MTU/0.24ms) were measured at 100Mbit/s, with bulking 8 packets, but the oscillating nature of the measurement indicate something, like sched latency might be causing this effect. More comparisons show, that this oscillation goes away occationally. Thus, we disregard this artifact completely and remove any "magic" bulking limit. For now, as a conservative approach, stop bulking when seeing TSO and segmented GSO packets. They already benefit from bulking on their own. A followup patch add this, to allow easier bisect-ability for finding regressions. Jointed work with Hannes, Daniel and Florian. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/sched/sch_generic.c46
1 files changed, 44 insertions, 2 deletions
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 7c8e5d7..c2e87e6 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -56,6 +56,41 @@ static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
return 0;
}
+static struct sk_buff *try_bulk_dequeue_skb(struct Qdisc *q,
+ struct sk_buff *head_skb,
+ int bytelimit)
+{
+ struct sk_buff *skb, *tail_skb = head_skb;
+
+ while (bytelimit > 0) {
+ /* For now, don't bulk dequeue GSO (or GSO segmented) pkts */
+ if (tail_skb->next || skb_is_gso(tail_skb))
+ break;
+
+ skb = q->dequeue(q);
+ if (!skb)
+ break;
+
+ bytelimit -= skb->len; /* covers GSO len */
+ skb = validate_xmit_skb(skb, qdisc_dev(q));
+ if (!skb)
+ break;
+
+ /* "skb" can be a skb list after validate call above
+ * (GSO segmented), but it is okay to append it to
+ * current tail_skb->next, because next round will exit
+ * in-case "tail_skb->next" is a skb list.
+ */
+ tail_skb->next = skb;
+ tail_skb = skb;
+ }
+
+ return head_skb;
+}
+
+/* Note that dequeue_skb can possibly return a SKB list (via skb->next).
+ * A requeued skb (via q->gso_skb) can also be a SKB list.
+ */
static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
{
struct sk_buff *skb = q->gso_skb;
@@ -70,10 +105,17 @@ static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
} else
skb = NULL;
} else {
- if (!(q->flags & TCQ_F_ONETXQUEUE) || !netif_xmit_frozen_or_stopped(txq)) {
+ if (!(q->flags & TCQ_F_ONETXQUEUE) ||
+ !netif_xmit_frozen_or_stopped(txq)) {
+ int bytelimit = qdisc_avail_bulklimit(txq);
+
skb = q->dequeue(q);
- if (skb)
+ if (skb) {
+ bytelimit -= skb->len;
skb = validate_xmit_skb(skb, qdisc_dev(q));
+ }
+ if (skb && qdisc_may_bulk(q))
+ skb = try_bulk_dequeue_skb(q, skb, bytelimit);
}
}
OpenPOWER on IntegriCloud