From 41acab8851a0408c1d5ad6c21a07456f88b54d40 Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Wed, 10 Mar 2010 23:37:45 -0300 Subject: sched: Implement group scheduler statistics in one struct Put all statistic fields of sched_entity in one struct, sched_statistics, and embed it into sched_entity. This change allows to memset the sched_statistics to 0 when needed (for instance when forking), avoiding bugs of non initialized fields. Signed-off-by: Lucas De Marchi Signed-off-by: Peter Zijlstra LKML-Reference: <1268275065-18542-1-git-send-email-lucas.de.marchi@gmail.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 47 +++++------------------- kernel/sched_debug.c | 101 +++++++++++++++++++-------------------------------- kernel/sched_fair.c | 65 +++++++++++++++++---------------- kernel/sched_rt.c | 2 +- 4 files changed, 81 insertions(+), 134 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 2c1db81f80eb..a4aa071f08f3 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2437,15 +2437,15 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, out_activate: #endif /* CONFIG_SMP */ - schedstat_inc(p, se.nr_wakeups); + schedstat_inc(p, se.statistics.nr_wakeups); if (wake_flags & WF_SYNC) - schedstat_inc(p, se.nr_wakeups_sync); + schedstat_inc(p, se.statistics.nr_wakeups_sync); if (orig_cpu != cpu) - schedstat_inc(p, se.nr_wakeups_migrate); + schedstat_inc(p, se.statistics.nr_wakeups_migrate); if (cpu == this_cpu) - schedstat_inc(p, se.nr_wakeups_local); + schedstat_inc(p, se.statistics.nr_wakeups_local); else - schedstat_inc(p, se.nr_wakeups_remote); + schedstat_inc(p, se.statistics.nr_wakeups_remote); activate_task(rq, p, 1); success = 1; @@ -2532,36 +2532,7 @@ static void __sched_fork(struct task_struct *p) p->se.avg_wakeup = sysctl_sched_wakeup_granularity; #ifdef CONFIG_SCHEDSTATS - p->se.wait_start = 0; - p->se.wait_max = 0; - p->se.wait_count = 0; - p->se.wait_sum = 0; - - p->se.sleep_start = 0; - p->se.sleep_max = 0; - p->se.sum_sleep_runtime = 0; - - p->se.block_start = 0; - p->se.block_max = 0; - p->se.exec_max = 0; - p->se.slice_max = 0; - - p->se.nr_migrations_cold = 0; - p->se.nr_failed_migrations_affine = 0; - p->se.nr_failed_migrations_running = 0; - p->se.nr_failed_migrations_hot = 0; - p->se.nr_forced_migrations = 0; - - p->se.nr_wakeups = 0; - p->se.nr_wakeups_sync = 0; - p->se.nr_wakeups_migrate = 0; - p->se.nr_wakeups_local = 0; - p->se.nr_wakeups_remote = 0; - p->se.nr_wakeups_affine = 0; - p->se.nr_wakeups_affine_attempts = 0; - p->se.nr_wakeups_passive = 0; - p->se.nr_wakeups_idle = 0; - + memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif INIT_LIST_HEAD(&p->rt.run_list); @@ -7910,9 +7881,9 @@ void normalize_rt_tasks(void) p->se.exec_start = 0; #ifdef CONFIG_SCHEDSTATS - p->se.wait_start = 0; - p->se.sleep_start = 0; - p->se.block_start = 0; + p->se.statistics.wait_start = 0; + p->se.statistics.sleep_start = 0; + p->se.statistics.block_start = 0; #endif if (!rt_task(p)) { diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 67f95aada4b9..ad9df4422763 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -70,16 +70,16 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, PN(se->vruntime); PN(se->sum_exec_runtime); #ifdef CONFIG_SCHEDSTATS - PN(se->wait_start); - PN(se->sleep_start); - PN(se->block_start); - PN(se->sleep_max); - PN(se->block_max); - PN(se->exec_max); - PN(se->slice_max); - PN(se->wait_max); - PN(se->wait_sum); - P(se->wait_count); + PN(se->statistics.wait_start); + PN(se->statistics.sleep_start); + PN(se->statistics.block_start); + PN(se->statistics.sleep_max); + PN(se->statistics.block_max); + PN(se->statistics.exec_max); + PN(se->statistics.slice_max); + PN(se->statistics.wait_max); + PN(se->statistics.wait_sum); + P(se->statistics.wait_count); #endif P(se->load.weight); #undef PN @@ -104,7 +104,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", SPLIT_NS(p->se.vruntime), SPLIT_NS(p->se.sum_exec_runtime), - SPLIT_NS(p->se.sum_sleep_runtime)); + SPLIT_NS(p->se.statistics.sum_sleep_runtime)); #else SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld", 0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L); @@ -413,34 +413,34 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) nr_switches = p->nvcsw + p->nivcsw; #ifdef CONFIG_SCHEDSTATS - PN(se.wait_start); - PN(se.sleep_start); - PN(se.block_start); - PN(se.sleep_max); - PN(se.block_max); - PN(se.exec_max); - PN(se.slice_max); - PN(se.wait_max); - PN(se.wait_sum); - P(se.wait_count); - PN(se.iowait_sum); - P(se.iowait_count); + PN(se.statistics.wait_start); + PN(se.statistics.sleep_start); + PN(se.statistics.block_start); + PN(se.statistics.sleep_max); + PN(se.statistics.block_max); + PN(se.statistics.exec_max); + PN(se.statistics.slice_max); + PN(se.statistics.wait_max); + PN(se.statistics.wait_sum); + P(se.statistics.wait_count); + PN(se.statistics.iowait_sum); + P(se.statistics.iowait_count); P(sched_info.bkl_count); P(se.nr_migrations); - P(se.nr_migrations_cold); - P(se.nr_failed_migrations_affine); - P(se.nr_failed_migrations_running); - P(se.nr_failed_migrations_hot); - P(se.nr_forced_migrations); - P(se.nr_wakeups); - P(se.nr_wakeups_sync); - P(se.nr_wakeups_migrate); - P(se.nr_wakeups_local); - P(se.nr_wakeups_remote); - P(se.nr_wakeups_affine); - P(se.nr_wakeups_affine_attempts); - P(se.nr_wakeups_passive); - P(se.nr_wakeups_idle); + P(se.statistics.nr_migrations_cold); + P(se.statistics.nr_failed_migrations_affine); + P(se.statistics.nr_failed_migrations_running); + P(se.statistics.nr_failed_migrations_hot); + P(se.statistics.nr_forced_migrations); + P(se.statistics.nr_wakeups); + P(se.statistics.nr_wakeups_sync); + P(se.statistics.nr_wakeups_migrate); + P(se.statistics.nr_wakeups_local); + P(se.statistics.nr_wakeups_remote); + P(se.statistics.nr_wakeups_affine); + P(se.statistics.nr_wakeups_affine_attempts); + P(se.statistics.nr_wakeups_passive); + P(se.statistics.nr_wakeups_idle); { u64 avg_atom, avg_per_cpu; @@ -491,32 +491,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) void proc_sched_set_task(struct task_struct *p) { #ifdef CONFIG_SCHEDSTATS - p->se.wait_max = 0; - p->se.wait_sum = 0; - p->se.wait_count = 0; - p->se.iowait_sum = 0; - p->se.iowait_count = 0; - p->se.sleep_max = 0; - p->se.sum_sleep_runtime = 0; - p->se.block_max = 0; - p->se.exec_max = 0; - p->se.slice_max = 0; - p->se.nr_migrations = 0; - p->se.nr_migrations_cold = 0; - p->se.nr_failed_migrations_affine = 0; - p->se.nr_failed_migrations_running = 0; - p->se.nr_failed_migrations_hot = 0; - p->se.nr_forced_migrations = 0; - p->se.nr_wakeups = 0; - p->se.nr_wakeups_sync = 0; - p->se.nr_wakeups_migrate = 0; - p->se.nr_wakeups_local = 0; - p->se.nr_wakeups_remote = 0; - p->se.nr_wakeups_affine = 0; - p->se.nr_wakeups_affine_attempts = 0; - p->se.nr_wakeups_passive = 0; - p->se.nr_wakeups_idle = 0; - p->sched_info.bkl_count = 0; + memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif p->se.sum_exec_runtime = 0; p->se.prev_sum_exec_runtime = 0; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 3e1fd96c6cf9..8ad164bbdac1 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -505,7 +505,8 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr, { unsigned long delta_exec_weighted; - schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max)); + schedstat_set(curr->statistics.exec_max, + max((u64)delta_exec, curr->statistics.exec_max)); curr->sum_exec_runtime += delta_exec; schedstat_add(cfs_rq, exec_clock, delta_exec); @@ -548,7 +549,7 @@ static void update_curr(struct cfs_rq *cfs_rq) static inline void update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) { - schedstat_set(se->wait_start, rq_of(cfs_rq)->clock); + schedstat_set(se->statistics.wait_start, rq_of(cfs_rq)->clock); } /* @@ -567,18 +568,18 @@ static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) static void update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) { - schedstat_set(se->wait_max, max(se->wait_max, - rq_of(cfs_rq)->clock - se->wait_start)); - schedstat_set(se->wait_count, se->wait_count + 1); - schedstat_set(se->wait_sum, se->wait_sum + - rq_of(cfs_rq)->clock - se->wait_start); + schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max, + rq_of(cfs_rq)->clock - se->statistics.wait_start)); + schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1); + schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum + + rq_of(cfs_rq)->clock - se->statistics.wait_start); #ifdef CONFIG_SCHEDSTATS if (entity_is_task(se)) { trace_sched_stat_wait(task_of(se), - rq_of(cfs_rq)->clock - se->wait_start); + rq_of(cfs_rq)->clock - se->statistics.wait_start); } #endif - schedstat_set(se->wait_start, 0); + schedstat_set(se->statistics.wait_start, 0); } static inline void @@ -657,39 +658,39 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) if (entity_is_task(se)) tsk = task_of(se); - if (se->sleep_start) { - u64 delta = rq_of(cfs_rq)->clock - se->sleep_start; + if (se->statistics.sleep_start) { + u64 delta = rq_of(cfs_rq)->clock - se->statistics.sleep_start; if ((s64)delta < 0) delta = 0; - if (unlikely(delta > se->sleep_max)) - se->sleep_max = delta; + if (unlikely(delta > se->statistics.sleep_max)) + se->statistics.sleep_max = delta; - se->sleep_start = 0; - se->sum_sleep_runtime += delta; + se->statistics.sleep_start = 0; + se->statistics.sum_sleep_runtime += delta; if (tsk) { account_scheduler_latency(tsk, delta >> 10, 1); trace_sched_stat_sleep(tsk, delta); } } - if (se->block_start) { - u64 delta = rq_of(cfs_rq)->clock - se->block_start; + if (se->statistics.block_start) { + u64 delta = rq_of(cfs_rq)->clock - se->statistics.block_start; if ((s64)delta < 0) delta = 0; - if (unlikely(delta > se->block_max)) - se->block_max = delta; + if (unlikely(delta > se->statistics.block_max)) + se->statistics.block_max = delta; - se->block_start = 0; - se->sum_sleep_runtime += delta; + se->statistics.block_start = 0; + se->statistics.sum_sleep_runtime += delta; if (tsk) { if (tsk->in_iowait) { - se->iowait_sum += delta; - se->iowait_count++; + se->statistics.iowait_sum += delta; + se->statistics.iowait_count++; trace_sched_stat_iowait(tsk, delta); } @@ -826,9 +827,9 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep) struct task_struct *tsk = task_of(se); if (tsk->state & TASK_INTERRUPTIBLE) - se->sleep_start = rq_of(cfs_rq)->clock; + se->statistics.sleep_start = rq_of(cfs_rq)->clock; if (tsk->state & TASK_UNINTERRUPTIBLE) - se->block_start = rq_of(cfs_rq)->clock; + se->statistics.block_start = rq_of(cfs_rq)->clock; } #endif } @@ -912,7 +913,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) * when there are only lesser-weight tasks around): */ if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) { - se->slice_max = max(se->slice_max, + se->statistics.slice_max = max(se->statistics.slice_max, se->sum_exec_runtime - se->prev_sum_exec_runtime); } #endif @@ -1306,7 +1307,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) if (sync && balanced) return 1; - schedstat_inc(p, se.nr_wakeups_affine_attempts); + schedstat_inc(p, se.statistics.nr_wakeups_affine_attempts); tl_per_task = cpu_avg_load_per_task(this_cpu); if (balanced || @@ -1318,7 +1319,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) * there is no bad imbalance. */ schedstat_inc(sd, ttwu_move_affine); - schedstat_inc(p, se.nr_wakeups_affine); + schedstat_inc(p, se.statistics.nr_wakeups_affine); return 1; } @@ -1844,13 +1845,13 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, * 3) are cache-hot on their current CPU. */ if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) { - schedstat_inc(p, se.nr_failed_migrations_affine); + schedstat_inc(p, se.statistics.nr_failed_migrations_affine); return 0; } *all_pinned = 0; if (task_running(rq, p)) { - schedstat_inc(p, se.nr_failed_migrations_running); + schedstat_inc(p, se.statistics.nr_failed_migrations_running); return 0; } @@ -1866,14 +1867,14 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, #ifdef CONFIG_SCHEDSTATS if (tsk_cache_hot) { schedstat_inc(sd, lb_hot_gained[idle]); - schedstat_inc(p, se.nr_forced_migrations); + schedstat_inc(p, se.statistics.nr_forced_migrations); } #endif return 1; } if (tsk_cache_hot) { - schedstat_inc(p, se.nr_failed_migrations_hot); + schedstat_inc(p, se.statistics.nr_failed_migrations_hot); return 0; } return 1; diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index c4fb42a66cab..0335e87f5204 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -613,7 +613,7 @@ static void update_curr_rt(struct rq *rq) if (unlikely((s64)delta_exec < 0)) delta_exec = 0; - schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec)); + schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec)); curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); -- cgit v1.2.3 From 9b33fa6ba0e2f90fdf407501db801c2511121564 Mon Sep 17 00:00:00 2001 From: "eranian@google.com" Date: Wed, 10 Mar 2010 22:26:05 -0800 Subject: perf_events: Improve task_sched_in() This patch is an optimization in perf_event_task_sched_in() to avoid scheduling the events twice in a row. Without it, the perf_disable()/perf_enable() pair is invoked twice, thereby pinned events counts while scheduling flexible events and we go throuh hw_perf_enable() twice. By encapsulating, the whole sequence into perf_disable()/perf_enable() we ensure, hw_perf_enable() is going to be invoked only once because of the refcount protection. Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra LKML-Reference: <1268288765-5326-1-git-send-email-eranian@google.com> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 52c69a34d697..3853d49c7d56 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -1368,6 +1368,8 @@ void perf_event_task_sched_in(struct task_struct *task) if (cpuctx->task_ctx == ctx) return; + perf_disable(); + /* * We want to keep the following priority order: * cpu pinned (that don't need to move), task pinned, @@ -1380,6 +1382,8 @@ void perf_event_task_sched_in(struct task_struct *task) ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE); cpuctx->task_ctx = ctx; + + perf_enable(); } #define MAX_INTERRUPTS (~0ULL) -- cgit v1.2.3 From 39c0cbe2150cbd848a25ba6cdb271d1ad46818ad Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:17:13 +0100 Subject: sched: Rate-limit nohz Entering nohz code on every micro-idle is costing ~10% throughput for netperf TCP_RR when scheduling cross-cpu. Rate limiting entry fixes this, but raises ticks a bit. On my Q6600, an idle box goes from ~85 interrupts/sec to 128. The higher the context switch rate, the more nohz entry costs. With this patch and some cycle recovery patches in my tree, max cross cpu context switch rate is improved by ~16%, a large portion of which of which is this ratelimiting. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301003.6785.28.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched.c | 12 ++++++++++++ kernel/time/tick-sched.c | 3 +++ 2 files changed, 15 insertions(+) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index a4aa071f08f3..60b1bbe2ad1b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -492,6 +492,7 @@ struct rq { #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; #ifdef CONFIG_NO_HZ + u64 nohz_stamp; unsigned char in_nohz_recently; #endif /* capture load from *all* tasks on this cpu: */ @@ -1228,6 +1229,17 @@ void wake_up_idle_cpu(int cpu) if (!tsk_is_polling(rq->idle)) smp_send_reschedule(cpu); } + +int nohz_ratelimit(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + u64 diff = rq->clock - rq->nohz_stamp; + + rq->nohz_stamp = rq->clock; + + return diff < (NSEC_PER_SEC / HZ) >> 1; +} + #endif /* CONFIG_NO_HZ */ static u64 sched_avg_period(void) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index f992762d7f51..f25735a767af 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -262,6 +262,9 @@ void tick_nohz_stop_sched_tick(int inidle) goto end; } + if (nohz_ratelimit(cpu)) + goto end; + ts->idle_calls++; /* Read jiffies and the time when jiffies were updated last */ do { -- cgit v1.2.3 From b42e0c41a422a212ddea0666d5a3a0e3c35206db Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:15:38 +0100 Subject: sched: Remove avg_wakeup Testing the load which led to this heuristic (nfs4 kbuild) shows that it has outlived it's usefullness. With intervening load balancing changes, I cannot see any difference with/without, so recover there fastpath cycles. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301062.6785.29.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched.c | 26 ++++---------------------- kernel/sched_debug.c | 1 - kernel/sched_fair.c | 31 ------------------------------- kernel/sched_features.h | 6 ------ 4 files changed, 4 insertions(+), 60 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 60b1bbe2ad1b..35a8626ace7d 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1880,9 +1880,6 @@ static void update_avg(u64 *avg, u64 sample) static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head) { - if (wakeup) - p->se.start_runtime = p->se.sum_exec_runtime; - sched_info_queued(p); p->sched_class->enqueue_task(rq, p, wakeup, head); p->se.on_rq = 1; @@ -1890,17 +1887,11 @@ enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head) static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep) { - if (sleep) { - if (p->se.last_wakeup) { - update_avg(&p->se.avg_overlap, - p->se.sum_exec_runtime - p->se.last_wakeup); - p->se.last_wakeup = 0; - } else { - update_avg(&p->se.avg_wakeup, - sysctl_sched_wakeup_granularity); - } + if (sleep && p->se.last_wakeup) { + update_avg(&p->se.avg_overlap, + p->se.sum_exec_runtime - p->se.last_wakeup); + p->se.last_wakeup = 0; } - sched_info_dequeued(p); p->sched_class->dequeue_task(rq, p, sleep); p->se.on_rq = 0; @@ -2466,13 +2457,6 @@ out_activate: */ if (!in_interrupt()) { struct sched_entity *se = ¤t->se; - u64 sample = se->sum_exec_runtime; - - if (se->last_wakeup) - sample -= se->last_wakeup; - else - sample -= se->start_runtime; - update_avg(&se->avg_wakeup, sample); se->last_wakeup = se->sum_exec_runtime; } @@ -2540,8 +2524,6 @@ static void __sched_fork(struct task_struct *p) p->se.nr_migrations = 0; p->se.last_wakeup = 0; p->se.avg_overlap = 0; - p->se.start_runtime = 0; - p->se.avg_wakeup = sysctl_sched_wakeup_granularity; #ifdef CONFIG_SCHEDSTATS memset(&p->se.statistics, 0, sizeof(p->se.statistics)); diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index ad9df4422763..20b95a420fec 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -408,7 +408,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) PN(se.vruntime); PN(se.sum_exec_runtime); PN(se.avg_overlap); - PN(se.avg_wakeup); nr_switches = p->nvcsw + p->nivcsw; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 8ad164bbdac1..6fc62854422c 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1592,42 +1592,11 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag } #endif /* CONFIG_SMP */ -/* - * Adaptive granularity - * - * se->avg_wakeup gives the average time a task runs until it does a wakeup, - * with the limit of wakeup_gran -- when it never does a wakeup. - * - * So the smaller avg_wakeup is the faster we want this task to preempt, - * but we don't want to treat the preemptee unfairly and therefore allow it - * to run for at least the amount of time we'd like to run. - * - * NOTE: we use 2*avg_wakeup to increase the probability of actually doing one - * - * NOTE: we use *nr_running to scale with load, this nicely matches the - * degrading latency on load. - */ -static unsigned long -adaptive_gran(struct sched_entity *curr, struct sched_entity *se) -{ - u64 this_run = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; - u64 expected_wakeup = 2*se->avg_wakeup * cfs_rq_of(se)->nr_running; - u64 gran = 0; - - if (this_run < expected_wakeup) - gran = expected_wakeup - this_run; - - return min_t(s64, gran, sysctl_sched_wakeup_granularity); -} - static unsigned long wakeup_gran(struct sched_entity *curr, struct sched_entity *se) { unsigned long gran = sysctl_sched_wakeup_granularity; - if (cfs_rq_of(curr)->curr && sched_feat(ADAPTIVE_GRAN)) - gran = adaptive_gran(curr, se); - /* * Since its curr running now, convert the gran from real-time * to virtual-time in his units. diff --git a/kernel/sched_features.h b/kernel/sched_features.h index d5059fd761d9..96ef5dbc66e1 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -30,12 +30,6 @@ SCHED_FEAT(START_DEBIT, 1) */ SCHED_FEAT(WAKEUP_PREEMPT, 1) -/* - * Compute wakeup_gran based on task behaviour, clipped to - * [0, sched_wakeup_gran_ns] - */ -SCHED_FEAT(ADAPTIVE_GRAN, 1) - /* * When converting the wakeup granularity to virtual time, do it such * that heavier tasks preempting a lighter task have an edge. -- cgit v1.2.3 From e12f31d3e5d36328c7fbd0fce40a95e70b59152c Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:15:51 +0100 Subject: sched: Remove avg_overlap Both avg_overlap and avg_wakeup had an inherent problem in that their accuracy was detrimentally affected by cross-cpu wakeups, this because we are missing the necessary call to update_curr(). This can't be fixed without increasing overhead in our already too fat fastpath. Additionally, with recent load balancing changes making us prefer to place tasks in an idle cache domain (which is good for compute bound loads), communicating tasks suffer when a sync wakeup, which would enable affine placement, is turned into a non-sync wakeup by SYNC_LESS. With one task on the runqueue, wake_affine() rejects the affine wakeup request, leaving the unfortunate where placed, taking frequent cache misses. Remove it, and recover some fastpath cycles. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301121.6785.30.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched.c | 33 --------------------------------- kernel/sched_debug.c | 1 - kernel/sched_fair.c | 18 ------------------ kernel/sched_features.h | 16 ---------------- 4 files changed, 68 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 35a8626ace7d..68ed6f4f3c13 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1887,11 +1887,6 @@ enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head) static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep) { - if (sleep && p->se.last_wakeup) { - update_avg(&p->se.avg_overlap, - p->se.sum_exec_runtime - p->se.last_wakeup); - p->se.last_wakeup = 0; - } sched_info_dequeued(p); p->sched_class->dequeue_task(rq, p, sleep); p->se.on_rq = 0; @@ -2452,15 +2447,6 @@ out_activate: activate_task(rq, p, 1); success = 1; - /* - * Only attribute actual wakeups done by this task. - */ - if (!in_interrupt()) { - struct sched_entity *se = ¤t->se; - - se->last_wakeup = se->sum_exec_runtime; - } - out_running: trace_sched_wakeup(rq, p, success); check_preempt_curr(rq, p, wake_flags); @@ -2522,8 +2508,6 @@ static void __sched_fork(struct task_struct *p) p->se.sum_exec_runtime = 0; p->se.prev_sum_exec_runtime = 0; p->se.nr_migrations = 0; - p->se.last_wakeup = 0; - p->se.avg_overlap = 0; #ifdef CONFIG_SCHEDSTATS memset(&p->se.statistics, 0, sizeof(p->se.statistics)); @@ -3594,23 +3578,6 @@ static inline void schedule_debug(struct task_struct *prev) static void put_prev_task(struct rq *rq, struct task_struct *prev) { - if (prev->state == TASK_RUNNING) { - u64 runtime = prev->se.sum_exec_runtime; - - runtime -= prev->se.prev_sum_exec_runtime; - runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost); - - /* - * In order to avoid avg_overlap growing stale when we are - * indeed overlapping and hence not getting put to sleep, grow - * the avg_overlap on preemption. - * - * We use the average preemption runtime because that - * correlates to the amount of cache footprint a task can - * build up. - */ - update_avg(&prev->se.avg_overlap, runtime); - } prev->sched_class->put_prev_task(rq, prev); } diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 20b95a420fec..8a46a719f367 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -407,7 +407,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) PN(se.exec_start); PN(se.vruntime); PN(se.sum_exec_runtime); - PN(se.avg_overlap); nr_switches = p->nvcsw + p->nivcsw; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 6fc62854422c..c3b69d4b5d65 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1241,7 +1241,6 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu, static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) { - struct task_struct *curr = current; unsigned long this_load, load; int idx, this_cpu, prev_cpu; unsigned long tl_per_task; @@ -1256,18 +1255,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) load = source_load(prev_cpu, idx); this_load = target_load(this_cpu, idx); - if (sync) { - if (sched_feat(SYNC_LESS) && - (curr->se.avg_overlap > sysctl_sched_migration_cost || - p->se.avg_overlap > sysctl_sched_migration_cost)) - sync = 0; - } else { - if (sched_feat(SYNC_MORE) && - (curr->se.avg_overlap < sysctl_sched_migration_cost && - p->se.avg_overlap < sysctl_sched_migration_cost)) - sync = 1; - } - /* * If sync wakeup then subtract the (maximum possible) * effect of the currently running task from the load @@ -1711,11 +1698,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ if (sched_feat(WAKEUP_SYNC) && sync) goto preempt; - if (sched_feat(WAKEUP_OVERLAP) && - se->avg_overlap < sysctl_sched_migration_cost && - pse->avg_overlap < sysctl_sched_migration_cost) - goto preempt; - if (!sched_feat(WAKEUP_PREEMPT)) return; diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 96ef5dbc66e1..c545e048dfed 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -41,12 +41,6 @@ SCHED_FEAT(ASYM_GRAN, 1) */ SCHED_FEAT(WAKEUP_SYNC, 0) -/* - * Wakeup preempt based on task behaviour. Tasks that do not overlap - * don't get preempted. - */ -SCHED_FEAT(WAKEUP_OVERLAP, 0) - /* * Use the SYNC wakeup hint, pipes and the likes use this to indicate * the remote end is likely to consume the data we just wrote, and @@ -63,16 +57,6 @@ SCHED_FEAT(SYNC_WAKEUPS, 1) */ SCHED_FEAT(AFFINE_WAKEUPS, 1) -/* - * Weaken SYNC hint based on overlap - */ -SCHED_FEAT(SYNC_LESS, 1) - -/* - * Add SYNC hint based on overlap - */ -SCHED_FEAT(SYNC_MORE, 0) - /* * Prefer to schedule the task we woke last (assuming it failed * wakeup-preemption), since its likely going to consume data we -- cgit v1.2.3 From a64692a3afd85fe048551ab89142fd5ca99a0dbd Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:16:20 +0100 Subject: sched: Cleanup/optimize clock updates Now that we no longer depend on the clock being updated prior to enqueueing on migratory wakeup, we can clean up a bit, placing calls to update_rq_clock() exactly where they are needed, ie on enqueue, dequeue and schedule events. In the case of a freshly enqueued task immediately preempting, we can skip the update during preemption, as the clock was just updated by the enqueue event. We also save an unneeded call during a migratory wakeup by not updating the previous runqueue, where update_curr() won't be invoked. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301199.6785.32.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched.c | 32 ++++++++++++++++---------------- kernel/sched_fair.c | 2 -- 2 files changed, 16 insertions(+), 18 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 68ed6f4f3c13..16559de4edea 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -495,6 +495,8 @@ struct rq { u64 nohz_stamp; unsigned char in_nohz_recently; #endif + unsigned int skip_clock_update; + /* capture load from *all* tasks on this cpu: */ struct load_weight load; unsigned long nr_load_updates; @@ -592,6 +594,13 @@ static inline void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) { rq->curr->sched_class->check_preempt_curr(rq, p, flags); + + /* + * A queue event has occurred, and we're going to schedule. In + * this case, we can save a useless back to back clock update. + */ + if (test_tsk_need_resched(p)) + rq->skip_clock_update = 1; } static inline int cpu_of(struct rq *rq) @@ -626,7 +635,8 @@ static inline int cpu_of(struct rq *rq) inline void update_rq_clock(struct rq *rq) { - rq->clock = sched_clock_cpu(cpu_of(rq)); + if (!rq->skip_clock_update) + rq->clock = sched_clock_cpu(cpu_of(rq)); } /* @@ -1782,8 +1792,6 @@ static void double_rq_lock(struct rq *rq1, struct rq *rq2) raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING); } } - update_rq_clock(rq1); - update_rq_clock(rq2); } /* @@ -1880,6 +1888,7 @@ static void update_avg(u64 *avg, u64 sample) static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head) { + update_rq_clock(rq); sched_info_queued(p); p->sched_class->enqueue_task(rq, p, wakeup, head); p->se.on_rq = 1; @@ -1887,6 +1896,7 @@ enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head) static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep) { + update_rq_clock(rq); sched_info_dequeued(p); p->sched_class->dequeue_task(rq, p, sleep); p->se.on_rq = 0; @@ -2366,7 +2376,6 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, smp_wmb(); rq = task_rq_lock(p, &flags); - update_rq_clock(rq); if (!(p->state & state)) goto out; @@ -2407,7 +2416,6 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, rq = cpu_rq(cpu); raw_spin_lock(&rq->lock); - update_rq_clock(rq); /* * We migrated the task without holding either rq->lock, however @@ -2624,7 +2632,6 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) BUG_ON(p->state != TASK_WAKING); p->state = TASK_RUNNING; - update_rq_clock(rq); activate_task(rq, p, 0); trace_sched_wakeup_new(rq, p, 1); check_preempt_curr(rq, p, WF_FORK); @@ -3578,6 +3585,9 @@ static inline void schedule_debug(struct task_struct *prev) static void put_prev_task(struct rq *rq, struct task_struct *prev) { + if (prev->se.on_rq) + update_rq_clock(rq); + rq->skip_clock_update = 0; prev->sched_class->put_prev_task(rq, prev); } @@ -3640,7 +3650,6 @@ need_resched_nonpreemptible: hrtick_clear(rq); raw_spin_lock_irq(&rq->lock); - update_rq_clock(rq); clear_tsk_need_resched(prev); if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { @@ -4197,7 +4206,6 @@ void rt_mutex_setprio(struct task_struct *p, int prio) BUG_ON(prio < 0 || prio > MAX_PRIO); rq = task_rq_lock(p, &flags); - update_rq_clock(rq); oldprio = p->prio; prev_class = p->sched_class; @@ -4240,7 +4248,6 @@ void set_user_nice(struct task_struct *p, long nice) * the task might be in the middle of scheduling on another CPU. */ rq = task_rq_lock(p, &flags); - update_rq_clock(rq); /* * The RT priorities are set via sched_setscheduler(), but we still * allow the 'normal' nice value to be set - but as expected @@ -4523,7 +4530,6 @@ recheck: raw_spin_unlock_irqrestore(&p->pi_lock, flags); goto recheck; } - update_rq_clock(rq); on_rq = p->se.on_rq; running = task_current(rq, p); if (on_rq) @@ -5530,7 +5536,6 @@ void sched_idle_next(void) __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1); - update_rq_clock(rq); activate_task(rq, p, 0); raw_spin_unlock_irqrestore(&rq->lock, flags); @@ -5585,7 +5590,6 @@ static void migrate_dead_tasks(unsigned int dead_cpu) for ( ; ; ) { if (!rq->nr_running) break; - update_rq_clock(rq); next = pick_next_task(rq); if (!next) break; @@ -5869,7 +5873,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) rq->migration_thread = NULL; /* Idle task back to normal (off runqueue, low prio) */ raw_spin_lock_irq(&rq->lock); - update_rq_clock(rq); deactivate_task(rq, rq->idle, 0); __setscheduler(rq, rq->idle, SCHED_NORMAL, 0); rq->idle->sched_class = &idle_sched_class; @@ -7815,7 +7818,6 @@ static void normalize_task(struct rq *rq, struct task_struct *p) { int on_rq; - update_rq_clock(rq); on_rq = p->se.on_rq; if (on_rq) deactivate_task(rq, p, 0); @@ -8177,8 +8179,6 @@ void sched_move_task(struct task_struct *tsk) rq = task_rq_lock(tsk, &flags); - update_rq_clock(rq); - running = task_current(rq, tsk); on_rq = tsk->se.on_rq; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index c3b69d4b5d65..69e582020ff8 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -3064,8 +3064,6 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu) /* move a task from busiest_rq to target_rq */ double_lock_balance(busiest_rq, target_rq); - update_rq_clock(busiest_rq); - update_rq_clock(target_rq); /* Search for an sd spanning us and the target CPU. */ for_each_domain(target_cpu, sd) { -- cgit v1.2.3 From 21406928afe43f1db6acab4931bb8c886f4d04ce Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:17:15 +0100 Subject: sched: Tweak sched_latency and min_granularity Allow LAST_BUDDY to kick in sooner, improving cache utilization as soon as a second buddy pair arrives on scene. The cost is latency starting to climb sooner, the tbenefit for tbench 8 on my Q6600 box is ~2%. No detrimental effects noted in normal idesktop usage. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301285.6785.34.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched_fair.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 69e582020ff8..d19df5bccfec 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -35,8 +35,8 @@ * (to see the precise effective timeslice length of your workload, * run vmstat and monitor the context-switches (cs) field) */ -unsigned int sysctl_sched_latency = 5000000ULL; -unsigned int normalized_sysctl_sched_latency = 5000000ULL; +unsigned int sysctl_sched_latency = 6000000ULL; +unsigned int normalized_sysctl_sched_latency = 6000000ULL; /* * The initial- and re-scaling of tunables is configurable @@ -52,15 +52,15 @@ enum sched_tunable_scaling sysctl_sched_tunable_scaling /* * Minimal preemption granularity for CPU-bound tasks: - * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds) + * (default: 2 msec * (1 + ilog(ncpus)), units: nanoseconds) */ -unsigned int sysctl_sched_min_granularity = 1000000ULL; -unsigned int normalized_sysctl_sched_min_granularity = 1000000ULL; +unsigned int sysctl_sched_min_granularity = 2000000ULL; +unsigned int normalized_sysctl_sched_min_granularity = 2000000ULL; /* * is kept at sysctl_sched_latency / sysctl_sched_min_granularity */ -static unsigned int sched_nr_latency = 5; +static unsigned int sched_nr_latency = 3; /* * After fork, child runs first. If set to 0 (default) then -- cgit v1.2.3 From 8b911acdf08477c059d1c36c21113ab1696c612b Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:17:16 +0100 Subject: sched: Fix select_idle_sibling() Don't bother with selection when the current cpu is idle. Recent load balancing changes also make it no longer necessary to check wake_affine() success before returning the selected sibling, so we now always use it. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301369.6785.36.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched_fair.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index d19df5bccfec..0008cc4a1199 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1439,7 +1439,7 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag int cpu = smp_processor_id(); int prev_cpu = task_cpu(p); int new_cpu = cpu; - int want_affine = 0; + int want_affine = 0, cpu_idle = !current->pid; int want_sd = 1; int sync = wake_flags & WF_SYNC; @@ -1497,13 +1497,15 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag * If there's an idle sibling in this domain, make that * the wake_affine target instead of the current cpu. */ - if (tmp->flags & SD_SHARE_PKG_RESOURCES) + if (!cpu_idle && tmp->flags & SD_SHARE_PKG_RESOURCES) target = select_idle_sibling(p, tmp, target); if (target >= 0) { if (tmp->flags & SD_WAKE_AFFINE) { affine_sd = tmp; want_affine = 0; + if (target != cpu) + cpu_idle = 1; } cpu = target; } @@ -1519,6 +1521,7 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag sd = tmp; } +#ifdef CONFIG_FAIR_GROUP_SCHED if (sched_feat(LB_SHARES_UPDATE)) { /* * Pick the largest domain to update shares over @@ -1532,9 +1535,12 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag if (tmp) update_shares(tmp); } +#endif - if (affine_sd && wake_affine(affine_sd, p, sync)) - return cpu; + if (affine_sd) { + if (cpu_idle || cpu == prev_cpu || wake_affine(affine_sd, p, sync)) + return cpu; + } while (sd) { int load_idx = sd->forkexec_idx; -- cgit v1.2.3 From 6bc6cf2b61336ed0c55a615eb4c0c8ed5daf3f08 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:17:17 +0100 Subject: sched: Remove NORMALIZED_SLEEPER This feature hasn't been enabled in a long time, remove effectively dead code. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301447.6785.38.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched_fair.c | 10 ---------- kernel/sched_features.h | 7 ------- 2 files changed, 17 deletions(-) (limited to 'kernel') diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 0008cc4a1199..de98e2e9d6e1 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -741,16 +741,6 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) if (!initial && sched_feat(FAIR_SLEEPERS)) { unsigned long thresh = sysctl_sched_latency; - /* - * Convert the sleeper threshold into virtual time. - * SCHED_IDLE is a special sub-class. We care about - * fairness only relative to other SCHED_IDLE tasks, - * all of which have the same weight. - */ - if (sched_feat(NORMALIZED_SLEEPER) && (!entity_is_task(se) || - task_of(se)->policy != SCHED_IDLE)) - thresh = calc_delta_fair(thresh, se); - /* * Halve their sleep time's effect, to allow * for a gentler effect of sleepers: diff --git a/kernel/sched_features.h b/kernel/sched_features.h index c545e048dfed..404288354aee 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -12,13 +12,6 @@ SCHED_FEAT(FAIR_SLEEPERS, 1) */ SCHED_FEAT(GENTLE_FAIR_SLEEPERS, 1) -/* - * By not normalizing the sleep time, heavy tasks get an effective - * longer period, and lighter task an effective shorter period they - * are considered running. - */ -SCHED_FEAT(NORMALIZED_SLEEPER, 0) - /* * Place new tasks ahead so that they do not starve already running * tasks -- cgit v1.2.3 From 5ca9880c6f4ba4c84b517bc2fed5366adf63d191 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:17:17 +0100 Subject: sched: Remove FAIR_SLEEPERS feature Our preemption model relies too heavily on sleeper fairness to disable it without dire consequences. Remove the feature, and save a branch or two. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301520.6785.40.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched_fair.c | 2 +- kernel/sched_features.h | 7 ------- 2 files changed, 1 insertion(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index de98e2e9d6e1..97682f925ed5 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -738,7 +738,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) vruntime += sched_vslice(cfs_rq, se); /* sleeps up to a single latency don't count. */ - if (!initial && sched_feat(FAIR_SLEEPERS)) { + if (!initial) { unsigned long thresh = sysctl_sched_latency; /* diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 404288354aee..850f9809cf81 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -1,10 +1,3 @@ -/* - * Disregards a certain amount of sleep time (sched_latency_ns) and - * considers the task to be running during that period. This gives it - * a service deficit on wakeup, allowing it to run sooner. - */ -SCHED_FEAT(FAIR_SLEEPERS, 1) - /* * Only give sleepers 50% of their service deficit. This allows * them to run sooner, but does not allow tons of sleepers to -- cgit v1.2.3 From f2e74eeac03ffb779d64b66a643c5e598145a28b Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:17:18 +0100 Subject: sched: Remove WAKEUP_SYNC feature This feature never earned its keep, remove it. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301591.6785.42.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched_fair.c | 4 ---- kernel/sched_features.h | 5 ----- 2 files changed, 9 deletions(-) (limited to 'kernel') diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 97682f925ed5..1d99535b0928 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1658,7 +1658,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ struct task_struct *curr = rq->curr; struct sched_entity *se = &curr->se, *pse = &p->se; struct cfs_rq *cfs_rq = task_cfs_rq(curr); - int sync = wake_flags & WF_SYNC; int scale = cfs_rq->nr_running >= sched_nr_latency; if (unlikely(rt_prio(p->prio))) @@ -1691,9 +1690,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ if (unlikely(curr->policy == SCHED_IDLE)) goto preempt; - if (sched_feat(WAKEUP_SYNC) && sync) - goto preempt; - if (!sched_feat(WAKEUP_PREEMPT)) return; diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 850f9809cf81..1cb7c4701bf3 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -22,11 +22,6 @@ SCHED_FEAT(WAKEUP_PREEMPT, 1) */ SCHED_FEAT(ASYM_GRAN, 1) -/* - * Always wakeup-preempt SYNC wakeups, see SYNC_WAKEUPS. - */ -SCHED_FEAT(WAKEUP_SYNC, 0) - /* * Use the SYNC wakeup hint, pipes and the likes use this to indicate * the remote end is likely to consume the data we just wrote, and -- cgit v1.2.3 From c6ee36c423c3ed1fb86bb3eabba9fc256a300d16 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:16:43 +0100 Subject: sched: Remove SYNC_WAKEUPS feature Sync wakeups are critical functionality with a long history. Remove it, we don't need the branch or icache footprint. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301817.6785.47.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched.c | 3 --- kernel/sched_features.h | 8 -------- 2 files changed, 11 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 16559de4edea..cc6dc8caa380 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2369,9 +2369,6 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, unsigned long flags; struct rq *rq; - if (!sched_feat(SYNC_WAKEUPS)) - wake_flags &= ~WF_SYNC; - this_cpu = get_cpu(); smp_wmb(); diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 1cb7c4701bf3..f54b6f9cc3dd 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -22,14 +22,6 @@ SCHED_FEAT(WAKEUP_PREEMPT, 1) */ SCHED_FEAT(ASYM_GRAN, 1) -/* - * Use the SYNC wakeup hint, pipes and the likes use this to indicate - * the remote end is likely to consume the data we just wrote, and - * therefore has cache benefit from being placed on the same cpu, see - * also AFFINE_WAKEUPS. - */ -SCHED_FEAT(SYNC_WAKEUPS, 1) - /* * Based on load and program behaviour, see if it makes sense to place * a newly woken task on the same cpu as the task that woke it -- -- cgit v1.2.3 From 13814d42e45dfbe845a0bbe5184565d9236896ae Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:17:04 +0100 Subject: sched: Remove ASYM_GRAN feature This features has been enabled for quite a while, after testing showed that easing preemption for light tasks was harmful to high priority threads. Remove the feature flag. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301675.6785.44.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched_fair.c | 28 +++++++++++----------------- kernel/sched_features.h | 6 ------ 2 files changed, 11 insertions(+), 23 deletions(-) (limited to 'kernel') diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 1d99535b0928..9357ecdb7f6b 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1583,24 +1583,18 @@ wakeup_gran(struct sched_entity *curr, struct sched_entity *se) /* * Since its curr running now, convert the gran from real-time * to virtual-time in his units. + * + * By using 'se' instead of 'curr' we penalize light tasks, so + * they get preempted easier. That is, if 'se' < 'curr' then + * the resulting gran will be larger, therefore penalizing the + * lighter, if otoh 'se' > 'curr' then the resulting gran will + * be smaller, again penalizing the lighter task. + * + * This is especially important for buddies when the leftmost + * task is higher priority than the buddy. */ - if (sched_feat(ASYM_GRAN)) { - /* - * By using 'se' instead of 'curr' we penalize light tasks, so - * they get preempted easier. That is, if 'se' < 'curr' then - * the resulting gran will be larger, therefore penalizing the - * lighter, if otoh 'se' > 'curr' then the resulting gran will - * be smaller, again penalizing the lighter task. - * - * This is especially important for buddies when the leftmost - * task is higher priority than the buddy. - */ - if (unlikely(se->load.weight != NICE_0_LOAD)) - gran = calc_delta_fair(gran, se); - } else { - if (unlikely(curr->load.weight != NICE_0_LOAD)) - gran = calc_delta_fair(gran, curr); - } + if (unlikely(se->load.weight != NICE_0_LOAD)) + gran = calc_delta_fair(gran, se); return gran; } diff --git a/kernel/sched_features.h b/kernel/sched_features.h index f54b6f9cc3dd..83c66e8ad3ee 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -16,12 +16,6 @@ SCHED_FEAT(START_DEBIT, 1) */ SCHED_FEAT(WAKEUP_PREEMPT, 1) -/* - * When converting the wakeup granularity to virtual time, do it such - * that heavier tasks preempting a lighter task have an edge. - */ -SCHED_FEAT(ASYM_GRAN, 1) - /* * Based on load and program behaviour, see if it makes sense to place * a newly woken task on the same cpu as the task that woke it -- -- cgit v1.2.3 From beac4c7e4a1cc6d57801f690e5e82fa2c9c245c8 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:17:20 +0100 Subject: sched: Remove AFFINE_WAKEUPS feature Disabling affine wakeups is too horrible to contemplate. Remove the feature flag. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301890.6785.50.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched_fair.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 9357ecdb7f6b..35a5c649638b 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1434,8 +1434,7 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag int sync = wake_flags & WF_SYNC; if (sd_flag & SD_BALANCE_WAKE) { - if (sched_feat(AFFINE_WAKEUPS) && - cpumask_test_cpu(cpu, &p->cpus_allowed)) + if (cpumask_test_cpu(cpu, &p->cpus_allowed)) want_affine = 1; new_cpu = prev_cpu; } -- cgit v1.2.3 From f55db609042faecd5e518ce372b87f846659b32e Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Thu, 11 Mar 2010 14:04:37 -0800 Subject: cpu-timers: Simplify RLIMIT_CPU handling Let always set signal->cputime_expires expiration cache when setting new itimer, POSIX 1.b timer, and RLIMIT_CPU. Since we are initializing prof_exp expiration cache during fork(), this allows to remove "RLIMIT_CPU != inf" check from fastpath_timer_check() and do some other cleanups. Checked against regression using test cases from: http://marc.info/?l=linux-kernel&m=123749066504641&w=4 http://marc.info/?l=linux-kernel&m=123811277916642&w=2 Signed-off-by: Stanislaw Gruszka Cc: Ingo Molnar Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Hidetoshi Seto Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner --- kernel/posix-cpu-timers.c | 75 +++++++++++++++++------------------------------ 1 file changed, 27 insertions(+), 48 deletions(-) (limited to 'kernel') diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 1a22dfd42df9..d01e0a348e61 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -11,19 +11,18 @@ #include /* - * Called after updating RLIMIT_CPU to set timer expiration if necessary. + * Called after updating RLIMIT_CPU to run cpu timer and update + * tsk->signal->cputime_expires expiration cache if necessary. Needs + * siglock protection since other code may update expiration cache as + * well. */ void update_rlimit_cpu(unsigned long rlim_new) { cputime_t cputime = secs_to_cputime(rlim_new); - struct signal_struct *const sig = current->signal; - if (cputime_eq(sig->it[CPUCLOCK_PROF].expires, cputime_zero) || - cputime_gt(sig->it[CPUCLOCK_PROF].expires, cputime)) { - spin_lock_irq(¤t->sighand->siglock); - set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL); - spin_unlock_irq(¤t->sighand->siglock); - } + spin_lock_irq(¤t->sighand->siglock); + set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL); + spin_unlock_irq(¤t->sighand->siglock); } static int check_clock(const clockid_t which_clock) @@ -564,7 +563,6 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now) struct list_head *head, *listpos; struct cpu_timer_list *const nt = &timer->it.cpu; struct cpu_timer_list *next; - unsigned long i; head = (CPUCLOCK_PERTHREAD(timer->it_clock) ? p->cpu_timers : p->signal->cpu_timers); @@ -630,20 +628,11 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now) default: BUG(); case CPUCLOCK_VIRT: - if (expires_le(sig->it[CPUCLOCK_VIRT].expires, - exp->cpu)) - break; - sig->cputime_expires.virt_exp = exp->cpu; - break; + if (expires_gt(sig->cputime_expires.virt_exp, exp->cpu)) + sig->cputime_expires.virt_exp = exp->cpu; case CPUCLOCK_PROF: - if (expires_le(sig->it[CPUCLOCK_PROF].expires, - exp->cpu)) - break; - i = sig->rlim[RLIMIT_CPU].rlim_cur; - if (i != RLIM_INFINITY && - i <= cputime_to_secs(exp->cpu)) - break; - sig->cputime_expires.prof_exp = exp->cpu; + if (expires_gt(sig->cputime_expires.prof_exp, exp->cpu)) + sig->cputime_expires.prof_exp = exp->cpu; break; case CPUCLOCK_SCHED: sig->cputime_expires.sched_exp = exp->sched; @@ -1386,7 +1375,7 @@ static inline int fastpath_timer_check(struct task_struct *tsk) return 1; } - return sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY; + return 0; } /* @@ -1452,21 +1441,23 @@ void run_posix_cpu_timers(struct task_struct *tsk) } /* - * Set one of the process-wide special case CPU timers. + * Set one of the process-wide special case CPU timers or RLIMIT_CPU. * The tsk->sighand->siglock must be held by the caller. - * The *newval argument is relative and we update it to be absolute, *oldval - * is absolute and we update it to be relative. */ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, cputime_t *newval, cputime_t *oldval) { union cpu_time_count now; - struct list_head *head; BUG_ON(clock_idx == CPUCLOCK_SCHED); cpu_timer_sample_group(clock_idx, tsk, &now); if (oldval) { + /* + * We are setting itimer. The *oldval is absolute and we update + * it to be relative, *newval argument is relative and we update + * it to be absolute. + */ if (!cputime_eq(*oldval, cputime_zero)) { if (cputime_le(*oldval, now.cpu)) { /* Just about to fire. */ @@ -1479,33 +1470,21 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, if (cputime_eq(*newval, cputime_zero)) return; *newval = cputime_add(*newval, now.cpu); - - /* - * If the RLIMIT_CPU timer will expire before the - * ITIMER_PROF timer, we have nothing else to do. - */ - if (tsk->signal->rlim[RLIMIT_CPU].rlim_cur - < cputime_to_secs(*newval)) - return; } /* - * Check whether there are any process timers already set to fire - * before this one. If so, we don't have anything more to do. + * Update expiration cache if we are the earliest timer, or eventually + * RLIMIT_CPU limit is earlier than prof_exp cpu timer expire. */ - head = &tsk->signal->cpu_timers[clock_idx]; - if (list_empty(head) || - cputime_ge(list_first_entry(head, - struct cpu_timer_list, entry)->expires.cpu, - *newval)) { - switch (clock_idx) { - case CPUCLOCK_PROF: + switch (clock_idx) { + case CPUCLOCK_PROF: + if (expires_gt(tsk->signal->cputime_expires.prof_exp, *newval)) tsk->signal->cputime_expires.prof_exp = *newval; - break; - case CPUCLOCK_VIRT: + break; + case CPUCLOCK_VIRT: + if (expires_gt(tsk->signal->cputime_expires.virt_exp, *newval)) tsk->signal->cputime_expires.virt_exp = *newval; - break; - } + break; } } -- cgit v1.2.3 From 5eb9aa6414bdab6d075a8763bc3b647181ef3aab Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Thu, 11 Mar 2010 14:04:38 -0800 Subject: cpu-timers: Cleanup arm_timer() Signed-off-by: Stanislaw Gruszka Cc: Ingo Molnar Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Hidetoshi Seto Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner --- kernel/posix-cpu-timers.c | 104 ++++++++++++++++------------------------------ 1 file changed, 35 insertions(+), 69 deletions(-) (limited to 'kernel') diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index d01e0a348e61..7c7166f766cc 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -547,97 +547,63 @@ static inline int expires_gt(cputime_t expires, cputime_t new_exp) cputime_gt(expires, new_exp); } -static inline int expires_le(cputime_t expires, cputime_t new_exp) -{ - return !cputime_eq(expires, cputime_zero) && - cputime_le(expires, new_exp); -} /* * Insert the timer on the appropriate list before any timers that * expire later. This must be called with the tasklist_lock held * for reading, and interrupts disabled. */ -static void arm_timer(struct k_itimer *timer, union cpu_time_count now) +static void arm_timer(struct k_itimer *timer) { struct task_struct *p = timer->it.cpu.task; struct list_head *head, *listpos; + struct task_cputime *cputime_expires; struct cpu_timer_list *const nt = &timer->it.cpu; struct cpu_timer_list *next; - head = (CPUCLOCK_PERTHREAD(timer->it_clock) ? - p->cpu_timers : p->signal->cpu_timers); + if (CPUCLOCK_PERTHREAD(timer->it_clock)) { + head = p->cpu_timers; + cputime_expires = &p->cputime_expires; + } else { + head = p->signal->cpu_timers; + cputime_expires = &p->signal->cputime_expires; + } head += CPUCLOCK_WHICH(timer->it_clock); BUG_ON(!irqs_disabled()); spin_lock(&p->sighand->siglock); listpos = head; - if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) { - list_for_each_entry(next, head, entry) { - if (next->expires.sched > nt->expires.sched) - break; - listpos = &next->entry; - } - } else { - list_for_each_entry(next, head, entry) { - if (cputime_gt(next->expires.cpu, nt->expires.cpu)) - break; - listpos = &next->entry; - } + list_for_each_entry(next, head, entry) { + if (cpu_time_before(timer->it_clock, nt->expires, next->expires)) + break; + listpos = &next->entry; } list_add(&nt->entry, listpos); if (listpos == head) { + union cpu_time_count *exp = &nt->expires; + /* - * We are the new earliest-expiring timer. - * If we are a thread timer, there can always - * be a process timer telling us to stop earlier. + * We are the new earliest-expiring POSIX 1.b timer, hence + * need to update expiration cache. Take into account that + * for process timers we share expiration cache with itimers + * and RLIMIT_CPU and for thread timers with RLIMIT_RTTIME. */ - if (CPUCLOCK_PERTHREAD(timer->it_clock)) { - union cpu_time_count *exp = &nt->expires; - - switch (CPUCLOCK_WHICH(timer->it_clock)) { - default: - BUG(); - case CPUCLOCK_PROF: - if (expires_gt(p->cputime_expires.prof_exp, - exp->cpu)) - p->cputime_expires.prof_exp = exp->cpu; - break; - case CPUCLOCK_VIRT: - if (expires_gt(p->cputime_expires.virt_exp, - exp->cpu)) - p->cputime_expires.virt_exp = exp->cpu; - break; - case CPUCLOCK_SCHED: - if (p->cputime_expires.sched_exp == 0 || - p->cputime_expires.sched_exp > exp->sched) - p->cputime_expires.sched_exp = - exp->sched; - break; - } - } else { - struct signal_struct *const sig = p->signal; - union cpu_time_count *exp = &timer->it.cpu.expires; - - /* - * For a process timer, set the cached expiration time. - */ - switch (CPUCLOCK_WHICH(timer->it_clock)) { - default: - BUG(); - case CPUCLOCK_VIRT: - if (expires_gt(sig->cputime_expires.virt_exp, exp->cpu)) - sig->cputime_expires.virt_exp = exp->cpu; - case CPUCLOCK_PROF: - if (expires_gt(sig->cputime_expires.prof_exp, exp->cpu)) - sig->cputime_expires.prof_exp = exp->cpu; - break; - case CPUCLOCK_SCHED: - sig->cputime_expires.sched_exp = exp->sched; - break; - } + switch (CPUCLOCK_WHICH(timer->it_clock)) { + case CPUCLOCK_PROF: + if (expires_gt(cputime_expires->prof_exp, exp->cpu)) + cputime_expires->prof_exp = exp->cpu; + break; + case CPUCLOCK_VIRT: + if (expires_gt(cputime_expires->virt_exp, exp->cpu)) + cputime_expires->virt_exp = exp->cpu; + break; + case CPUCLOCK_SCHED: + if (cputime_expires->sched_exp == 0 || + cputime_expires->sched_exp > exp->sched) + cputime_expires->sched_exp = exp->sched; + break; } } @@ -819,7 +785,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags, if (new_expires.sched != 0 && (timer->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE && cpu_time_before(timer->it_clock, val, new_expires)) { - arm_timer(timer, val); + arm_timer(timer); } read_unlock(&tasklist_lock); @@ -1283,7 +1249,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer) /* * Now re-arm for the new expiry time. */ - arm_timer(timer, now); + arm_timer(timer); out_unlock: read_unlock(&tasklist_lock); -- cgit v1.2.3 From ae1a78eecc45fe41215d9dbfd7079999455772d6 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Thu, 11 Mar 2010 14:04:39 -0800 Subject: cpu-timers: Return correct previous timer reload value According POSIX we need to correctly set old timer it_interval value when user request that in timer_settime(). Tested using below program. #include #include #include #include #include #include #include int main(void) { struct sigaction act; struct sigevent evt = { }; timer_t tid; struct itimerspec spec, u_spec, k_spec; evt.sigev_notify = SIGEV_SIGNAL; evt.sigev_signo = SIGPROF; assert(timer_create(CLOCK_PROCESS_CPUTIME_ID, &evt, &tid) == 0); spec.it_value.tv_sec = 1; spec.it_value.tv_nsec = 2; spec.it_interval.tv_sec = 3; spec.it_interval.tv_nsec = 4; u_spec = spec; assert(timer_settime(tid, 0, &spec, NULL) == 0); spec.it_value.tv_sec = 5; spec.it_value.tv_nsec = 6; spec.it_interval.tv_sec = 7; spec.it_interval.tv_nsec = 8; assert(timer_settime(tid, 0, &spec, &k_spec) == 0); #define PRT(val) printf(#val ":\t%d/%d\n", (int) u_spec.val, (int) k_spec.val) PRT(it_value.tv_sec); PRT(it_value.tv_nsec); PRT(it_interval.tv_sec); PRT(it_interval.tv_nsec); return 0; } Signed-off-by: Stanislaw Gruszka Cc: Ingo Molnar Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Hidetoshi Seto Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner --- kernel/posix-cpu-timers.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 7c7166f766cc..cce2f0b2d406 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -676,7 +676,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags, struct itimerspec *new, struct itimerspec *old) { struct task_struct *p = timer->it.cpu.task; - union cpu_time_count old_expires, new_expires, val; + union cpu_time_count old_expires, new_expires, old_incr, val; int ret; if (unlikely(p == NULL)) { @@ -707,6 +707,7 @@ int posix_cpu_timer