From c10d73671ad30f54692f7f69f0e09e75d3a8926a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 10 Jan 2013 15:26:34 -0800 Subject: 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 Cc: David Miller Cc: Tom Herbert Cc: Ben Hutchings Signed-off-by: David S. Miller --- kernel/softirq.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'kernel') 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(); -- cgit v1.2.2 From ca2eb5679f8ddffff60156af42595df44a315ef0 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 5 Feb 2013 07:25:17 +0000 Subject: tcp: remove Appropriate Byte Count support TCP Appropriate Byte Count was added by me, but later disabled. There is no point in maintaining it since it is a potential source of bugs and Linux already implements other better window protection heuristics. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- kernel/sysctl_binary.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 5a6384450501..b669ca1fa103 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -387,7 +387,6 @@ static const struct bin_table bin_net_ipv4_table[] = { { CTL_INT, NET_TCP_MODERATE_RCVBUF, "tcp_moderate_rcvbuf" }, { CTL_INT, NET_TCP_TSO_WIN_DIVISOR, "tcp_tso_win_divisor" }, { CTL_STR, NET_TCP_CONG_CONTROL, "tcp_congestion_control" }, - { CTL_INT, NET_TCP_ABC, "tcp_abc" }, { CTL_INT, NET_TCP_MTU_PROBING, "tcp_mtu_probing" }, { CTL_INT, NET_TCP_BASE_MSS, "tcp_base_mss" }, { CTL_INT, NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS, "tcp_workaround_signed_windows" }, -- cgit v1.2.2