Techwizz/kernel-fxtec-pro1x
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

softirq: reduce latencies

Browse source 
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>
This commit is contained in:
Eric Dumazet 2013-01-10 15:26:34 -08:00 committed by David S. Miller
parent 1def9238d4
commit c10d73671a
1 changed files with 9 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
kernel/softirq.c
View file

@ -195,21 +195,21 @@ void local_bh_enable_ip(unsigned long ip)
EXPORT_SYMBOL(local_bh_enable_ip); EXPORT_SYMBOL(local_bh_enable_ip);
/* /*
* We restart softirq processing MAX_SOFTIRQ_RESTART times, * We restart softirq processing for at most 2 ms,
* and we fall back to softirqd after that. * 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 - * The two things to balance is latency against fairness -
* we want to handle softirqs as soon as possible, but they * we want to handle softirqs as soon as possible, but they
* should not be able to lock up the box. * 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) asmlinkage void __do_softirq(void)
{ {
struct softirq_action *h; struct softirq_action *h;
__u32 pending; __u32 pending;
int max_restart = MAX_SOFTIRQ_RESTART; unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
int cpu; int cpu;
unsigned long old_flags = current->flags; unsigned long old_flags = current->flags;
@ -264,11 +264,12 @@ asmlinkage void __do_softirq(void)
local_irq_disable(); local_irq_disable();
pending = local_softirq_pending(); pending = local_softirq_pending();
if (pending && --max_restart) if (pending) {
goto restart; if (time_before(jiffies, end) && !need_resched())
goto restart;
if (pending)
wakeup_softirqd(); wakeup_softirqd();
}
lockdep_softirq_exit(); lockdep_softirq_exit();