aboutsummaryrefslogtreecommitdiffstats
path: root/net/sched/sch_hfsc.c
diff options
context:
space:
mode:
authorEric Dumazet <edumazet@google.com>2016-06-06 09:37:16 -0700
committerDavid S. Miller <davem@davemloft.net>2016-06-07 16:37:14 -0700
commitedb09eb17ed89eaa82a52dd306beac93e292b485 (patch)
tree1f241506d6b781b65d1033925f1c1ce6a39c3394 /net/sched/sch_hfsc.c
parentnet_sched: transform qdisc running bit into a seqcount (diff)
downloadlinux-dev-edb09eb17ed89eaa82a52dd306beac93e292b485.tar.xz
linux-dev-edb09eb17ed89eaa82a52dd306beac93e292b485.zip
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_hfsc.c')
-rw-r--r--net/sched/sch_hfsc.c10
1 files changed, 5 insertions, 5 deletions
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index d783d7cc3348..74813dd49053 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1015,11 +1015,10 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
cur_time = psched_get_time();
if (tca[TCA_RATE]) {
- spinlock_t *lock = qdisc_root_sleeping_lock(sch);
-
err = gen_replace_estimator(&cl->bstats, NULL,
&cl->rate_est,
- lock,
+ NULL,
+ qdisc_root_sleeping_running(sch),
tca[TCA_RATE]);
if (err)
return err;
@@ -1068,7 +1067,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
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);
@@ -1373,7 +1373,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
xstats.work = cl->cl_total;
xstats.rtwork = cl->cl_cumul;
- 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->qdisc->q.qlen) < 0)
return -1;