xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

net: sched: avoid costly atomic operation in fq_dequeue()

Browse Source 
Standard qdisc API to setup a timer implies an atomic operation on every
packet dequeue : qdisc_unthrottled()

It turns out this is not really needed for FQ, as FQ has no concept of
global qdisc throttling, being a qdisc handling many different flows,
some of them can be throttled, while others are not.

Fix is straightforward : add a 'bool throttle' to
qdisc_watchdog_schedule_ns(), and remove calls to qdisc_unthrottled()
in sch_fq.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Eric Dumazet
2014-10-04 10:11:31 -07:00
committed by David S. Miller
parent 681d2421e1
commit f2600cf02b
4 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
net/sched/sch_fq.c
View File

@@ -377,7 +377,6 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
if (time_after(jiffies, f->age + q->flow_refill_delay))
f->credit = max_t(u32, f->credit, q->quantum);
q->inactive_flows--;
qdisc_unthrottled(sch);
}
/* Note: this overwrites f->age */
@@ -385,7 +384,6 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
if (unlikely(f == &q->internal)) {
q->stat_internal_packets++;
qdisc_unthrottled(sch);
}
sch->q.qlen++;
@@ -433,7 +431,8 @@ begin:
if (!head->first) {
if (q->time_next_delayed_flow != ~0ULL)
qdisc_watchdog_schedule_ns(&q->watchdog,
q->time_next_delayed_flow);
q->time_next_delayed_flow,
false);
return NULL;
}
}
@@ -495,7 +494,6 @@ begin:
}
out:
qdisc_bstats_update(sch, skb);
qdisc_unthrottled(sch);
return skb;
}