summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorEric Dumazet <edumazet@google.com>2013-01-10 15:26:34 -0800
committerDavid S. Miller <davem@davemloft.net>2013-01-10 15:33:01 -0800
commitc10d73671ad30f54692f7f69f0e09e75d3a8926a (patch)
treeef875858caef802617a3f54183a344361c0151b7
parent1def9238d4aa2146924994aa4b7dc861f03b9362 (diff)
softirq: reduce latencies
In various network workloads, __do_softirq() latencies can be up to 20 ms if HZ=1000, and 200 ms if HZ=100. This is because we iterate 10 times in the softirq dispatcher, and some actions can consume a lot of cycles. This patch changes the fallback to ksoftirqd condition to : - A time limit of 2 ms. - need_resched() being set on current task When one of this condition is met, we wakeup ksoftirqd for further softirq processing if we still have pending softirqs. Using need_resched() as the only condition can trigger RCU stalls, as we can keep BH disabled for too long. I ran several benchmarks and got no significant difference in throughput, but a very significant reduction of latencies (one order of magnitude) : In following bench, 200 antagonist "netperf -t TCP_RR" are started in background, using all available cpus. Then we start one "netperf -t TCP_RR", bound to the cpu handling the NIC IRQ (hard+soft) Before patch : # netperf -H 7.7.7.84 -t TCP_RR -T2,2 -- -k RT_LATENCY,MIN_LATENCY,MAX_LATENCY,P50_LATENCY,P90_LATENCY,P99_LATENCY,MEAN_LATENCY,STDDEV_LATENCY MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.7.84 () port 0 AF_INET : first burst 0 : cpu bind RT_LATENCY=550110.424 MIN_LATENCY=146858 MAX_LATENCY=997109 P50_LATENCY=305000 P90_LATENCY=550000 P99_LATENCY=710000 MEAN_LATENCY=376989.12 STDDEV_LATENCY=184046.92 After patch : # netperf -H 7.7.7.84 -t TCP_RR -T2,2 -- -k RT_LATENCY,MIN_LATENCY,MAX_LATENCY,P50_LATENCY,P90_LATENCY,P99_LATENCY,MEAN_LATENCY,STDDEV_LATENCY MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.7.84 () port 0 AF_INET : first burst 0 : cpu bind RT_LATENCY=40545.492 MIN_LATENCY=9834 MAX_LATENCY=78366 P50_LATENCY=33583 P90_LATENCY=59000 P99_LATENCY=69000 MEAN_LATENCY=38364.67 STDDEV_LATENCY=12865.26 Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: David Miller <davem@davemloft.net> Cc: Tom Herbert <therbert@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--kernel/softirq.c17
1 files changed, 9 insertions, 8 deletions
diff --git a/kernel/softirq.c b/kernel/softirq.c
index ed567babe789..47cb991c6ba4 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -195,21 +195,21 @@ void local_bh_enable_ip(unsigned long ip)
EXPORT_SYMBOL(local_bh_enable_ip);
/*
- * We restart softirq processing MAX_SOFTIRQ_RESTART times,
- * and we fall back to softirqd after that.
+ * We restart softirq processing for at most 2 ms,
+ * and if need_resched() is not set.
*
- * This number has been established via experimentation.
+ * These limits have been established via experimentation.
* The two things to balance is latency against fairness -
* we want to handle softirqs as soon as possible, but they
* should not be able to lock up the box.
*/
-#define MAX_SOFTIRQ_RESTART 10
+#define MAX_SOFTIRQ_TIME msecs_to_jiffies(2)
asmlinkage void __do_softirq(void)
{
struct softirq_action *h;
__u32 pending;
- int max_restart = MAX_SOFTIRQ_RESTART;
+ unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
int cpu;
unsigned long old_flags = current->flags;
@@ -264,11 +264,12 @@ restart:
local_irq_disable();
pending = local_softirq_pending();
- if (pending && --max_restart)
- goto restart;
+ if (pending) {
+ if (time_before(jiffies, end) && !need_resched())
+ goto restart;
- if (pending)
wakeup_softirqd();
+ }
lockdep_softirq_exit();