From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756162Ab0JTWtl (ORCPT ); Wed, 20 Oct 2010 18:49:41 -0400 Received: from smtp-out.google.com ([216.239.44.51]:32248 "EHLO smtp-out.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756144Ab0JTWtj (ORCPT ); Wed, 20 Oct 2010 18:49:39 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=google.com; s=beta; h=from:to:cc:subject:date:message-id:x-mailer:in-reply-to:references; b=YM9GjvulvxGLm8YEwrX+OPFl+mHosDI9F14OUPZF6yC2pSmEyTq8Q5yI6fHBJH9RBS 87qMrNuPtupi4klOVlJg== From: Venkatesh Pallipadi To: Peter Zijlstra , Ingo Molnar , "H. Peter Anvin" , Thomas Gleixner , Balbir Singh , Martin Schwidefsky Cc: linux-kernel@vger.kernel.org, Paul Turner , Eric Dumazet , Shaun Ruffell , Yong Zhang , Venkatesh Pallipadi Subject: [PATCH 4/6] Export ns irqtimes from IRQ_TIME_ACCOUNTING through /proc/stat Date: Wed, 20 Oct 2010 15:49:00 -0700 Message-Id: <1287614941-32325-5-git-send-email-venki@google.com> X-Mailer: git-send-email 1.7.1 In-Reply-To: <1287614941-32325-1-git-send-email-venki@google.com> References: <1287614941-32325-1-git-send-email-venki@google.com> X-System-Of-Record: true Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org CONFIG_IRQ_TIME_ACCOUNTING adds ns granularity irq time on each CPU. This info is already used in scheduler to do proper task chargeback (earlier patches). This patch retro-fits this ns granularity hardirq and softirq information to /proc/stat irq and softirq fields. The update is still done on timer tick, where we look at accumulated ns hardirq/softirq time and account the tick to user/system/irq/hardirq/guest accordingly. No new interface added. Earlier versions looked at adding this as new fields in some /proc files. This one seems to be the best in terms of impact to existing apps, even though it has somewhat more kernel code than earlier versions. Signed-off-by: Venkatesh Pallipadi --- kernel/sched.c | 102 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 files changed, 102 insertions(+), 0 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 8b97958..7e812a6 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2002,8 +2002,40 @@ static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) } } +static int irqtime_account_hi_update(void) +{ + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + unsigned long flags; + u64 latest_ns; + int ret = 0; + + local_irq_save(flags); + latest_ns = __get_cpu_var(cpu_hardirq_time); + if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->irq)) + ret = 1; + local_irq_restore(flags); + return ret; +} + +static int irqtime_account_si_update(void) +{ + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + unsigned long flags; + u64 latest_ns; + int ret = 0; + + local_irq_save(flags); + latest_ns = __get_cpu_var(cpu_softirq_time); + if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->softirq)) + ret = 1; + local_irq_restore(flags); + return ret; +} + #else +#define sched_clock_irqtime (0) + static u64 irq_time_cpu(int cpu) { return 0; @@ -3554,6 +3586,65 @@ void account_system_time(struct task_struct *p, int hardirq_offset, __account_system_time(p, cputime, cputime_scaled, target_cputime64); } +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +/* + * Account a tick to a process and cpustat + * @p: the process that the cpu time gets accounted to + * @user_tick: is the tick from userspace + * @rq: the pointer to rq + * + * Tick demultiplexing follows the order + * - pending hardirq update + * - user_time + * - pending softirq update + * - idle_time + * - system time + * - check for guest_time + * - else account as system_time + * + * Check for hardirq is done both for system and user time as there is + * no timer going off while we are on hardirq and hence we may never get an + * oppurtunity to update it solely in system time. + * p->stime and friends are only updated on system time and not on irq + * softirq as those do not count in task exec_runtime any more. + */ +static void irqtime_account_process_tick(struct task_struct *p, int user_tick, + struct rq *rq) +{ + cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy); + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + + if (irqtime_account_hi_update()) { + cpustat->irq = cputime64_add(cpustat->irq, tmp); + } else if (user_tick) { + account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); + } else if (irqtime_account_si_update()) { + cpustat->softirq = cputime64_add(cpustat->softirq, tmp); + } else if (p == rq->idle) { + account_idle_time(cputime_one_jiffy); + } else if (p->flags & PF_VCPU) { /* System time or guest time */ + account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled); + } else { + __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, + &cpustat->system); + } +} + +static void irqtime_account_idle_ticks(int ticks) +{ + int i; + struct rq *rq = this_rq(); + + for (i = 0; i < ticks; i++) + irqtime_account_process_tick(current, 0, rq); +} +#else +static void irqtime_account_idle_ticks(int ticks) {} +static void irqtime_account_process_tick(struct task_struct *p, int user_tick, + struct rq *rq) {} +#endif + /* * Account for involuntary wait time. * @steal: the cpu time spent in involuntary wait @@ -3594,6 +3685,11 @@ void account_process_tick(struct task_struct *p, int user_tick) cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); struct rq *rq = this_rq(); + if (sched_clock_irqtime) { + irqtime_account_process_tick(p, user_tick, rq); + return; + } + if (user_tick) account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) @@ -3619,6 +3715,12 @@ void account_steal_ticks(unsigned long ticks) */ void account_idle_ticks(unsigned long ticks) { + + if (sched_clock_irqtime) { + irqtime_account_idle_ticks(ticks); + return; + } + account_idle_time(jiffies_to_cputime(ticks)); } -- 1.7.1