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 <[email protected]>
Cc: Cong Wang <[email protected]>
Cc: Jamal Hadi Salim <[email protected]>
Cc: John Fastabend <[email protected]>
Cc: Kevin Athey <[email protected]>
Cc: Xiaotian Pei <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
index 610cd39..231e121 100644
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -33,10 +33,12 @@
spinlock_t *lock, struct gnet_dump *d,
int padattr);
-int gnet_stats_copy_basic(struct gnet_dump *d,
+int gnet_stats_copy_basic(const seqcount_t *running,
+ struct gnet_dump *d,
struct gnet_stats_basic_cpu __percpu *cpu,
struct gnet_stats_basic_packed *b);
-void __gnet_stats_copy_basic(struct gnet_stats_basic_packed *bstats,
+void __gnet_stats_copy_basic(const seqcount_t *running,
+ struct gnet_stats_basic_packed *bstats,
struct gnet_stats_basic_cpu __percpu *cpu,
struct gnet_stats_basic_packed *b);
int gnet_stats_copy_rate_est(struct gnet_dump *d,
@@ -52,13 +54,15 @@
int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
struct gnet_stats_basic_cpu __percpu *cpu_bstats,
struct gnet_stats_rate_est64 *rate_est,
- spinlock_t *stats_lock, struct nlattr *opt);
+ spinlock_t *stats_lock,
+ seqcount_t *running, struct nlattr *opt);
void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
struct gnet_stats_rate_est64 *rate_est);
int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
struct gnet_stats_basic_cpu __percpu *cpu_bstats,
struct gnet_stats_rate_est64 *rate_est,
- spinlock_t *stats_lock, struct nlattr *opt);
+ spinlock_t *stats_lock,
+ seqcount_t *running, struct nlattr *opt);
bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
const struct gnet_stats_rate_est64 *rate_est);
#endif
