From 8f0dfc34e9b323a028c2ec41abb7e9de477b7a94 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Mon, 20 Jul 2009 11:26:58 -0700 Subject: sched: Provide iowait counters For counting how long an application has been waiting for (disk) IO, there currently is only the HZ sample driven information available, while for all other counters in this class, a high resolution version is available via CONFIG_SCHEDSTATS. In order to make an improved bootchart tool possible, we also need a higher resolution version of the iowait time. This patch below adds this scheduler statistic to the kernel. Signed-off-by: Arjan van de Ven Signed-off-by: Peter Zijlstra LKML-Reference: <4A64B813.1080506@linux.intel.com> Signed-off-by: Ingo Molnar --- kernel/sched_debug.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel/sched_debug.c') diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 70c7e0b79946..5ddbd0891267 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -409,6 +409,8 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) PN(se.wait_max); PN(se.wait_sum); P(se.wait_count); + PN(se.iowait_sum); + P(se.iowait_count); P(sched_info.bkl_count); P(se.nr_migrations); P(se.nr_migrations_cold); @@ -479,6 +481,8 @@ void proc_sched_set_task(struct task_struct *p) 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; -- cgit v1.2.3 From ad4b78bbcbab66998b05d422ac6106b645796e54 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Sep 2009 12:31:31 +0200 Subject: sched: Add new wakeup preemption mode: WAKEUP_RUNNING Create a new wakeup preemption mode, preempt towards tasks that run shorter on avg. It sets next buddy to be sure we actually run the task we preempted for. Test results: root@twins:~# while :; do :; done & [1] 6537 root@twins:~# while :; do :; done & [2] 6538 root@twins:~# while :; do :; done & [3] 6539 root@twins:~# while :; do :; done & [4] 6540 root@twins:/home/peter# ./latt -c4 sleep 4 Entries: 48 (clients=4) Averages: ------------------------------ Max 4750 usec Avg 497 usec Stdev 737 usec root@twins:/home/peter# echo WAKEUP_RUNNING > /debug/sched_features root@twins:/home/peter# ./latt -c4 sleep 4 Entries: 48 (clients=4) Averages: ------------------------------ Max 14 usec Avg 5 usec Stdev 3 usec Disabled by default - needs more testing. Signed-off-by: Peter Zijlstra Acked-by: Mike Galbraith Signed-off-by: Ingo Molnar LKML-Reference: --- include/linux/sched.h | 2 ++ kernel/sched.c | 17 ++++++++++------- kernel/sched_debug.c | 1 + kernel/sched_fair.c | 14 +++++++++++--- kernel/sched_features.h | 5 +++++ 5 files changed, 29 insertions(+), 10 deletions(-) (limited to 'kernel/sched_debug.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index b4a39bb2b4a4..8af3d249170e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1113,6 +1113,8 @@ struct sched_entity { u64 start_runtime; u64 avg_wakeup; + u64 avg_running; + #ifdef CONFIG_SCHEDSTATS u64 wait_start; u64 wait_max; diff --git a/kernel/sched.c b/kernel/sched.c index 969dfaef2465..3bb4ea2ee6f0 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2458,6 +2458,7 @@ static void __sched_fork(struct task_struct *p) p->se.avg_overlap = 0; p->se.start_runtime = 0; p->se.avg_wakeup = sysctl_sched_wakeup_granularity; + p->se.avg_running = 0; #ifdef CONFIG_SCHEDSTATS p->se.wait_start = 0; @@ -5310,14 +5311,13 @@ static inline void schedule_debug(struct task_struct *prev) #endif } -static void put_prev_task(struct rq *rq, struct task_struct *prev) +static void put_prev_task(struct rq *rq, struct task_struct *p) { - if (prev->state == TASK_RUNNING) { - u64 runtime = prev->se.sum_exec_runtime; + u64 runtime = p->se.sum_exec_runtime - p->se.prev_sum_exec_runtime; - runtime -= prev->se.prev_sum_exec_runtime; - runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost); + update_avg(&p->se.avg_running, runtime); + if (p->state == TASK_RUNNING) { /* * In order to avoid avg_overlap growing stale when we are * indeed overlapping and hence not getting put to sleep, grow @@ -5327,9 +5327,12 @@ static void put_prev_task(struct rq *rq, struct task_struct *prev) * correlates to the amount of cache footprint a task can * build up. */ - update_avg(&prev->se.avg_overlap, runtime); + runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost); + update_avg(&p->se.avg_overlap, runtime); + } else { + update_avg(&p->se.avg_running, 0); } - prev->sched_class->put_prev_task(rq, prev); + p->sched_class->put_prev_task(rq, p); } /* diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 5ddbd0891267..efb84409bc43 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -395,6 +395,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) PN(se.sum_exec_runtime); PN(se.avg_overlap); PN(se.avg_wakeup); + PN(se.avg_running); nr_switches = p->nvcsw + p->nivcsw; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index c741cd9d38de..3e6f78c66876 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1605,9 +1605,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ return; } - if (!sched_feat(WAKEUP_PREEMPT)) - return; - if ((sched_feat(WAKEUP_SYNC) && sync) || (sched_feat(WAKEUP_OVERLAP) && (se->avg_overlap < sysctl_sched_migration_cost && @@ -1616,6 +1613,17 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ return; } + if (sched_feat(WAKEUP_RUNNING)) { + if (pse->avg_running < se->avg_running) { + set_next_buddy(pse); + resched_task(curr); + return; + } + } + + if (!sched_feat(WAKEUP_PREEMPT)) + return; + find_matching_se(&se, &pse); BUG_ON(!pse); diff --git a/kernel/sched_features.h b/kernel/sched_features.h index d5059fd761d9..0d94083582c7 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -53,6 +53,11 @@ SCHED_FEAT(WAKEUP_SYNC, 0) */ SCHED_FEAT(WAKEUP_OVERLAP, 0) +/* + * Wakeup preemption towards tasks that run short + */ +SCHED_FEAT(WAKEUP_RUNNING, 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