From 2c2d9624697fc5e7dd84490ae01b80cc43ec2def Mon Sep 17 00:00:00 2001 From: Chuyi Zhou Date: Wed, 17 Jul 2024 22:33:42 +0800 Subject: sched/fair: Remove cfs_rq::nr_spread_over and cfs_rq::exec_clock nr_spread_over tracks the number of instances where the difference between a scheduling entity's virtual runtime and the minimum virtual runtime in the runqueue exceeds three times the scheduler latency, indicating significant disparity in task scheduling. Commit that removed its usage: 5e963f2bd: sched/fair: Commit to EEVDF cfs_rq->exec_clock was used to account for time spent executing tasks. Commit that removed its usage: 5d69eca542ee1 sched: Unify runtime accounting across classes cfs_rq::nr_spread_over and cfs_rq::exec_clock are not used anymore in eevdf. Remove them from struct cfs_rq. Signed-off-by: Chuyi Zhou Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Chengming Zhou Reviewed-by: K Prateek Nayak Acked-by: Vishal Chourasia Link: https://lore.kernel.org/r/20240717143342.593262-1-zhouchuyi@bytedance.com --- kernel/sched/debug.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index c1eb9a1afd13..90c4a9998377 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -641,8 +641,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) SEQ_printf(m, "\n"); SEQ_printf(m, "cfs_rq[%d]:\n", cpu); #endif - SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "exec_clock", - SPLIT_NS(cfs_rq->exec_clock)); raw_spin_rq_lock_irqsave(rq, flags); root = __pick_root_entity(cfs_rq); @@ -669,8 +667,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) SPLIT_NS(right_vruntime)); spread = right_vruntime - left_vruntime; SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread", SPLIT_NS(spread)); - SEQ_printf(m, " .%-30s: %d\n", "nr_spread_over", - cfs_rq->nr_spread_over); SEQ_printf(m, " .%-30s: %d\n", "nr_running", cfs_rq->nr_running); SEQ_printf(m, " .%-30s: %d\n", "h_nr_running", cfs_rq->h_nr_running); SEQ_printf(m, " .%-30s: %d\n", "idle_nr_running", -- cgit v1.2.3 From d741f297bceaf52aa1b97b997708fc0cd853c73e Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Mon, 27 May 2024 14:06:52 +0200 Subject: sched/fair: Fair server interface Add an interface for fair server setup on debugfs. Each CPU has two files under /debug/sched/fair_server/cpu{ID}: - runtime: set runtime in ns - period: set period in ns This then leaves /proc/sys/kernel/sched_rt_{period,runtime}_us to set bounds on admission control. The interface also add the server to the dl bandwidth accounting. Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Peter Zijlstra (Intel) Tested-by: Juri Lelli Link: https://lore.kernel.org/r/a9ef9fc69bcedb44bddc9bc34f2b313296052819.1716811044.git.bristot@kernel.org --- kernel/sched/debug.c | 159 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 159 insertions(+) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 90c4a9998377..72f2715dec78 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -333,8 +333,165 @@ static const struct file_operations sched_debug_fops = { .release = seq_release, }; +enum dl_param { + DL_RUNTIME = 0, + DL_PERIOD, +}; + +static unsigned long fair_server_period_max = (1 << 22) * NSEC_PER_USEC; /* ~4 seconds */ +static unsigned long fair_server_period_min = (100) * NSEC_PER_USEC; /* 100 us */ + +static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos, enum dl_param param) +{ + long cpu = (long) ((struct seq_file *) filp->private_data)->private; + struct rq *rq = cpu_rq(cpu); + u64 runtime, period; + size_t err; + int retval; + u64 value; + + err = kstrtoull_from_user(ubuf, cnt, 10, &value); + if (err) + return err; + + scoped_guard (rq_lock_irqsave, rq) { + runtime = rq->fair_server.dl_runtime; + period = rq->fair_server.dl_period; + + switch (param) { + case DL_RUNTIME: + if (runtime == value) + break; + runtime = value; + break; + case DL_PERIOD: + if (value == period) + break; + period = value; + break; + } + + if (runtime > period || + period > fair_server_period_max || + period < fair_server_period_min) { + return -EINVAL; + } + + if (rq->cfs.h_nr_running) { + update_rq_clock(rq); + dl_server_stop(&rq->fair_server); + } + + retval = dl_server_apply_params(&rq->fair_server, runtime, period, 0); + if (retval) + cnt = retval; + + if (!runtime) + printk_deferred("Fair server disabled in CPU %d, system may crash due to starvation.\n", + cpu_of(rq)); + + if (rq->cfs.h_nr_running) + dl_server_start(&rq->fair_server); + } + + *ppos += cnt; + return cnt; +} + +static size_t sched_fair_server_show(struct seq_file *m, void *v, enum dl_param param) +{ + unsigned long cpu = (unsigned long) m->private; + struct rq *rq = cpu_rq(cpu); + u64 value; + + switch (param) { + case DL_RUNTIME: + value = rq->fair_server.dl_runtime; + break; + case DL_PERIOD: + value = rq->fair_server.dl_period; + break; + } + + seq_printf(m, "%llu\n", value); + return 0; + +} + +static ssize_t +sched_fair_server_runtime_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return sched_fair_server_write(filp, ubuf, cnt, ppos, DL_RUNTIME); +} + +static int sched_fair_server_runtime_show(struct seq_file *m, void *v) +{ + return sched_fair_server_show(m, v, DL_RUNTIME); +} + +static int sched_fair_server_runtime_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, sched_fair_server_runtime_show, inode->i_private); +} + +static const struct file_operations fair_server_runtime_fops = { + .open = sched_fair_server_runtime_open, + .write = sched_fair_server_runtime_write, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static ssize_t +sched_fair_server_period_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return sched_fair_server_write(filp, ubuf, cnt, ppos, DL_PERIOD); +} + +static int sched_fair_server_period_show(struct seq_file *m, void *v) +{ + return sched_fair_server_show(m, v, DL_PERIOD); +} + +static int sched_fair_server_period_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, sched_fair_server_period_show, inode->i_private); +} + +static const struct file_operations fair_server_period_fops = { + .open = sched_fair_server_period_open, + .write = sched_fair_server_period_write, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static struct dentry *debugfs_sched; +static void debugfs_fair_server_init(void) +{ + struct dentry *d_fair; + unsigned long cpu; + + d_fair = debugfs_create_dir("fair_server", debugfs_sched); + if (!d_fair) + return; + + for_each_possible_cpu(cpu) { + struct dentry *d_cpu; + char buf[32]; + + snprintf(buf, sizeof(buf), "cpu%lu", cpu); + d_cpu = debugfs_create_dir(buf, d_fair); + + debugfs_create_file("runtime", 0644, d_cpu, (void *) cpu, &fair_server_runtime_fops); + debugfs_create_file("period", 0644, d_cpu, (void *) cpu, &fair_server_period_fops); + } +} + static __init int sched_init_debug(void) { struct dentry __maybe_unused *numa; @@ -374,6 +531,8 @@ static __init int sched_init_debug(void) debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops); + debugfs_fair_server_init(); + return 0; } late_initcall(sched_init_debug); -- cgit v1.2.3 From 5f6bd380c7bdbe10f7b4e8ddcceed60ce0714c6d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 27 May 2024 14:06:55 +0200 Subject: sched/rt: Remove default bandwidth control Now that fair_server exists, we no longer need RT bandwidth control unless RT_GROUP_SCHED. Enable fair_server with parameters equivalent to RT throttling. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: "Peter Zijlstra (Intel)" Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: "Vineeth Pillai (Google)" Signed-off-by: Peter Zijlstra (Intel) Tested-by: Juri Lelli Link: https://lore.kernel.org/r/14d562db55df5c3c780d91940743acb166895ef7.1716811044.git.bristot@kernel.org --- kernel/sched/debug.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 72f2715dec78..e75914e7d2a8 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -885,9 +885,12 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x)) PU(rt_nr_running); + +#ifdef CONFIG_RT_GROUP_SCHED P(rt_throttled); PN(rt_time); PN(rt_runtime); +#endif #undef PN #undef PU -- cgit v1.2.3 From 4ae0c2b91110dab6f4291c2c7f99dde60ecc97d8 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 1 Aug 2024 10:44:03 -0500 Subject: sched/debug: Fix fair_server_period_max value This code has an integer overflow or sign extension bug which was caught by gcc-13: kernel/sched/debug.c:341:57: error: integer overflow in expression of type 'long int' results in '-100663296' [-Werror=overflow] 341 | static unsigned long fair_server_period_max = (1 << 22) * NSEC_PER_USEC; /* ~4 seconds */ The result is that "fair_server_period_max" is set to 0xfffffffffa000000 (585 years) instead of instead of 0xfa000000 (4 seconds) that was intended. Fix this by changing the type to shift from (1 << 22) to (1UL << 22). Closes: https://lore.kernel.org/all/CA+G9fYtE2GAbeqU+AOCffgo2oH0RTJUxU+=Pi3cFn4di_KgBAQ@mail.gmail.com/ Fixes: d741f297bcea ("sched/fair: Fair server interface") Reported-by: Linux Kernel Functional Testing Reported-by: Arnd Bergmann Reported-by: Stephen Rothwell Signed-off-by: Dan Carpenter Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/a936b991-e464-4bdf-94ab-08e25d364986@stanley.mountain --- kernel/sched/debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index e75914e7d2a8..831a77ab8466 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -338,7 +338,7 @@ enum dl_param { DL_PERIOD, }; -static unsigned long fair_server_period_max = (1 << 22) * NSEC_PER_USEC; /* ~4 seconds */ +static unsigned long fair_server_period_max = (1UL << 22) * NSEC_PER_USEC; /* ~4 seconds */ static unsigned long fair_server_period_min = (100) * NSEC_PER_USEC; /* 100 us */ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubuf, -- cgit v1.2.3 From 857b158dc5e81c6de795ef6be006eed146098fc6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 22 May 2023 13:46:30 +0200 Subject: sched/eevdf: Use sched_attr::sched_runtime to set request/slice suggestion Allow applications to directly set a suggested request/slice length using sched_attr::sched_runtime. The implementation clamps the value to: 0.1[ms] <= slice <= 100[ms] which is 1/10 the size of HZ=1000 and 10 times the size of HZ=100. Applications should strive to use their periodic runtime at a high confidence interval (95%+) as the target slice. Using a smaller slice will introduce undue preemptions, while using a larger value will increase latency. For all the following examples assume a scheduling quantum of 8, and for consistency all examples have W=4: {A,B,C,D}(w=1,r=8): ABCD... +---+---+---+--- t=0, V=1.5 t=1, V=3.5 A |------< A |------< B |------< B |------< C |------< C |------< D |------< D |------< ---+*------+-------+--- ---+--*----+-------+--- t=2, V=5.5 t=3, V=7.5 A |------< A |------< B |------< B |------< C |------< C |------< D |------< D |------< ---+----*--+-------+--- ---+------*+-------+--- Note: 4 identical tasks in FIFO order ~~~ {A,B}(w=1,r=16) C(w=2,r=16) AACCBBCC... +---+---+---+--- t=0, V=1.25 t=2, V=5.25 A |--------------< A |--------------< B |--------------< B |--------------< C |------< C |------< ---+*------+-------+--- ---+----*--+-------+--- t=4, V=8.25 t=6, V=12.25 A |--------------< A |--------------< B |--------------< B |--------------< C |------< C |------< ---+-------*-------+--- ---+-------+---*---+--- Note: 1 heavy task -- because q=8, double r such that the deadline of the w=2 task doesn't go below q. Note: observe the full schedule becomes: W*max(r_i/w_i) = 4*2q = 8q in length. Note: the period of the heavy task is half the full period at: W*(r_i/w_i) = 4*(2q/2) = 4q ~~~ {A,C,D}(w=1,r=16) B(w=1,r=8): BAACCBDD... +---+---+---+--- t=0, V=1.5 t=1, V=3.5 A |--------------< A |---------------< B |------< B |------< C |--------------< C |--------------< D |--------------< D |--------------< ---+*------+-------+--- ---+--*----+-------+--- t=3, V=7.5 t=5, V=11.5 A |---------------< A |---------------< B |------< B |------< C |--------------< C |--------------< D |--------------< D |--------------< ---+------*+-------+--- ---+-------+--*----+--- t=6, V=13.5 A |---------------< B |------< C |--------------< D |--------------< ---+-------+----*--+--- Note: 1 short task -- again double r so that the deadline of the short task won't be below q. Made B short because its not the leftmost task, but is eligible with the 0,1,2,3 spread. Note: like with the heavy task, the period of the short task observes: W*(r_i/w_i) = 4*(1q/1) = 4q ~~~ A(w=1,r=16) B(w=1,r=8) C(w=2,r=16) BCCAABCC... +---+---+---+--- t=0, V=1.25 t=1, V=3.25 A |--------------< A |--------------< B |------< B |------< C |------< C |------< ---+*------+-------+--- ---+--*----+-------+--- t=3, V=7.25 t=5, V=11.25 A |--------------< A |--------------< B |------< B |------< C |------< C |------< ---+------*+-------+--- ---+-------+--*----+--- t=6, V=13.25 A |--------------< B |------< C |------< ---+-------+----*--+--- Note: 1 heavy and 1 short task -- combine them all. Note: both the short and heavy task end up with a period of 4q ~~~ A(w=1,r=16) B(w=2,r=16) C(w=1,r=8) BBCAABBC... +---+---+---+--- t=0, V=1 t=2, V=5 A |--------------< A |--------------< B |------< B |------< C |------< C |------< ---+*------+-------+--- ---+----*--+-------+--- t=3, V=7 t=5, V=11 A |--------------< A |--------------< B |------< B |------< C |------< C |------< ---+------*+-------+--- ---+-------+--*----+--- t=7, V=15 A |--------------< B |------< C |------< ---+-------+------*+--- Note: as before but permuted ~~~ From all this it can be deduced that, for the steady state: - the total period (P) of a schedule is: W*max(r_i/w_i) - the average period of a task is: W*(r_i/w_i) - each task obtains the fair share: w_i/W of each full period P Signed-off-by: Peter Zijlstra (Intel) Tested-by: Valentin Schneider Link: https://lkml.kernel.org/r/20240727105030.842834421@infradead.org --- kernel/sched/debug.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 831a77ab8466..01ce9a76164c 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -739,11 +739,12 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) else SEQ_printf(m, " %c", task_state_to_char(p)); - SEQ_printf(m, "%15s %5d %9Ld.%06ld %c %9Ld.%06ld %9Ld.%06ld %9Ld.%06ld %9Ld %5d ", + SEQ_printf(m, "%15s %5d %9Ld.%06ld %c %9Ld.%06ld %c %9Ld.%06ld %9Ld.%06ld %9Ld %5d ", p->comm, task_pid_nr(p), SPLIT_NS(p->se.vruntime), entity_eligible(cfs_rq_of(&p->se), &p->se) ? 'E' : 'N', SPLIT_NS(p->se.deadline), + p->se.custom_slice ? 'S' : ' ', SPLIT_NS(p->se.slice), SPLIT_NS(p->se.sum_exec_runtime), (long long)(p->nvcsw + p->nivcsw), -- cgit v1.2.3 From 2cab4bd024d23f658e40dce209dfd012f4e8b19a Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Fri, 6 Sep 2024 13:30:19 +0800 Subject: sched/debug: Fix the runnable tasks output The current runnable tasks output looks like: runnable tasks: S task PID tree-key switches prio wait-time sum-exec sum-sleep ------------------------------------------------------------------------------------------------------------- Ikworker/R-rcu_g 4 0.129049 E 0.620179 0.750000 0.002920 2 100 0.000000 0.002920 0.000000 0.000000 0 0 / Ikworker/R-sync_ 5 0.125328 E 0.624147 0.750000 0.001840 2 100 0.000000 0.001840 0.000000 0.000000 0 0 / Ikworker/R-slub_ 6 0.120835 E 0.628680 0.750000 0.001800 2 100 0.000000 0.001800 0.000000 0.000000 0 0 / Ikworker/R-netns 7 0.114294 E 0.634701 0.750000 0.002400 2 100 0.000000 0.002400 0.000000 0.000000 0 0 / I kworker/0:1 9 508.781746 E 511.754666 3.000000 151.575240 224 120 0.000000 151.575240 0.000000 0.000000 0 0 / Which is messy. Remove the duplicate printing of sum_exec_runtime and tidy up the layout to make it look like: runnable tasks: S task PID vruntime eligible deadline slice sum-exec switches prio wait-time sum-sleep sum-block node group-id group-path ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- I kworker/0:3 1698 295.001459 E 297.977619 3.000000 38.862920 9 120 0.000000 0.000000 0.000000 0 0 / I kworker/0:4 1702 278.026303 E 281.026303 3.000000 9.918760 3 120 0.000000 0.000000 0.000000 0 0 / S NetworkManager 2646 0.377936 E 2.598104 3.000000 98.535880 314 120 0.000000 0.000000 0.000000 0 0 /system.slice/NetworkManager.service S virtqemud 2689 0.541016 E 2.440104 3.000000 50.967960 80 120 0.000000 0.000000 0.000000 0 0 /system.slice/virtqemud.service S gsd-smartcard 3058 73.604144 E 76.475904 3.000000 74.033320 88 120 0.000000 0.000000 0.000000 0 0 /user.slice/user-42.slice/session-c1.scope Reviewed-by: Christoph Lameter (Ampere) Signed-off-by: Huang Shijie Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20240906053019.7874-1-shijie@os.amperecomputing.com --- kernel/sched/debug.c | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 01ce9a76164c..de1dc5264b3f 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -739,7 +739,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) else SEQ_printf(m, " %c", task_state_to_char(p)); - SEQ_printf(m, "%15s %5d %9Ld.%06ld %c %9Ld.%06ld %c %9Ld.%06ld %9Ld.%06ld %9Ld %5d ", + SEQ_printf(m, " %15s %5d %9Ld.%06ld %c %9Ld.%06ld %c %9Ld.%06ld %9Ld.%06ld %9Ld %5d ", p->comm, task_pid_nr(p), SPLIT_NS(p->se.vruntime), entity_eligible(cfs_rq_of(&p->se), &p->se) ? 'E' : 'N', @@ -750,17 +750,16 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) (long long)(p->nvcsw + p->nivcsw), p->prio); - SEQ_printf(m, "%9lld.%06ld %9lld.%06ld %9lld.%06ld %9lld.%06ld", + SEQ_printf(m, "%9lld.%06ld %9lld.%06ld %9lld.%06ld", SPLIT_NS(schedstat_val_or_zero(p->stats.wait_sum)), - SPLIT_NS(p->se.sum_exec_runtime), SPLIT_NS(schedstat_val_or_zero(p->stats.sum_sleep_runtime)), SPLIT_NS(schedstat_val_or_zero(p->stats.sum_block_runtime))); #ifdef CONFIG_NUMA_BALANCING - SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p)); + SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p)); #endif #ifdef CONFIG_CGROUP_SCHED - SEQ_printf_task_group_path(m, task_group(p), " %s") + SEQ_printf_task_group_path(m, task_group(p), " %s") #endif SEQ_printf(m, "\n"); @@ -772,10 +771,26 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) SEQ_printf(m, "\n"); SEQ_printf(m, "runnable tasks:\n"); - SEQ_printf(m, " S task PID tree-key switches prio" - " wait-time sum-exec sum-sleep\n"); + SEQ_printf(m, " S task PID vruntime eligible " + "deadline slice sum-exec switches " + "prio wait-time sum-sleep sum-block" +#ifdef CONFIG_NUMA_BALANCING + " node group-id" +#endif +#ifdef CONFIG_CGROUP_SCHED + " group-path" +#endif + "\n"); SEQ_printf(m, "-------------------------------------------------------" - "------------------------------------------------------\n"); + "------------------------------------------------------" + "------------------------------------------------------" +#ifdef CONFIG_NUMA_BALANCING + "--------------" +#endif +#ifdef CONFIG_CGROUP_SCHED + "--------------" +#endif + "\n"); rcu_read_lock(); for_each_process_thread(g, p) { -- cgit v1.2.3