summaryrefslogtreecommitdiff
path: root/net/sched/sch_cbq.c
diff options
context:
space:
mode:
authorEric Dumazet <edumazet@google.com>2016-06-06 19:37:16 +0300
committerDavid S. Miller <davem@davemloft.net>2016-06-08 02:37:14 +0300
commitedb09eb17ed89eaa82a52dd306beac93e292b485 (patch)
tree1f241506d6b781b65d1033925f1c1ce6a39c3394 /net/sched/sch_cbq.c
parentf9eb8aea2a1e12fc2f584d1627deeb957435a801 (diff)
downloadlinux-edb09eb17ed89eaa82a52dd306beac93e292b485.tar.xz
net: sched: do not acquire qdisc spinlock in qdisc/class stats dump
Large tc dumps (tc -s {qdisc|class} sh dev ethX) done by Google BwE host agent [1] are problematic at scale : For each qdisc/class found in the dump, we currently lock the root qdisc spinlock in order to get stats. Sampling stats every 5 seconds from thousands of HTB classes is a challenge when the root qdisc spinlock is under high pressure. Not only the dumps take time, they also slow down the fast path (queue/dequeue packets) by 10 % to 20 % in some cases. An audit of existing qdiscs showed that sch_fq_codel is the only qdisc that might need the qdisc lock in fq_codel_dump_stats() and fq_codel_dump_class_stats() In v2 of this patch, I now use the Qdisc running seqcount to provide consistent reads of packets/bytes counters, regardless of 32/64 bit arches. I also changed rate estimators to use the same infrastructure so that they no longer need to lock root qdisc lock. [1] http://static.googleusercontent.com/media/research.google.com/en//pubs/archive/43838.pdf Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: Kevin Athey <kda@google.com> Cc: Xiaotian Pei <xiaotian@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/sched/sch_cbq.c')
-rw-r--r--net/sched/sch_cbq.c9
1 files changed, 6 insertions, 3 deletions
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index baafddf229ce..1b8128fb845d 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1600,7 +1600,8 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
if (cl->undertime != PSCHED_PASTPERFECT)
cl->xstats.undertime = cl->undertime - q->now;
- if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
+ if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+ d, NULL, &cl->bstats) < 0 ||
gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->q->q.qlen) < 0)
return -1;
@@ -1755,7 +1756,8 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
if (tca[TCA_RATE]) {
err = gen_replace_estimator(&cl->bstats, NULL,
&cl->rate_est,
- qdisc_root_sleeping_lock(sch),
+ NULL,
+ qdisc_root_sleeping_running(sch),
tca[TCA_RATE]);
if (err) {
qdisc_put_rtab(rtab);
@@ -1848,7 +1850,8 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
if (tca[TCA_RATE]) {
err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est,
- qdisc_root_sleeping_lock(sch),
+ NULL,
+ qdisc_root_sleeping_running(sch),
tca[TCA_RATE]);
if (err) {
kfree(cl);