system/linux
system/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux synced 2024-07-23 11:39:11 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
linux/init/init_task.c
Qais Yousef 22d5607400 sched/fair: Check if a task has a fitting CPU when updating misfit 
If a misfit task is affined to a subset of the possible CPUs, we need to
verify that one of these CPUs can fit it. Otherwise the load balancer
code will continuously trigger needlessly leading the balance_interval
to increase in return and eventually end up with a situation where real
imbalances take a long time to address because of this impossible
imbalance situation.

This can happen in Android world where it's common for background tasks
to be restricted to little cores.

Similarly if we can't fit the biggest core, triggering misfit is
pointless as it is the best we can ever get on this system.

To be able to detect that; we use asym_cap_list to iterate through
capacities in the system to see if the task is able to run at a higher
capacity level based on its p->cpus_ptr. We do that when the affinity
change, a fair task is forked, or when a task switched to fair policy.
We store the max_allowed_capacity in task_struct to allow for cheap
comparison in the fast path.

Improve check_misfit_status() function by removing redundant checks.
misfit_task_load will be 0 if the task can't move to a bigger CPU. And
nohz_balancer_kick() already checks for cpu_check_capacity() before
calling check_misfit_status().

Test:
=====

Add

	trace_printk("balance_interval = %lu\n", interval)

in get_sd_balance_interval().

run
	if [ "$MASK" != "0" ]; then
		adb shell "taskset -a $MASK cat /dev/zero > /dev/null"
	fi
	sleep 10
	// parse ftrace buffer counting the occurrence of each valaue

Where MASK is either:

	* 0: no busy task running
	* 1: busy task is pinned to 1 cpu; handled today to not cause
	  misfit
	* f: busy task pinned to little cores, simulates busy background
	  task, demonstrates the problem to be fixed

Results:
========

Note how occurrence of balance_interval = 128 overshoots for MASK = f.

BEFORE
------

	MASK=0

		   1 balance_interval = 175
		 120 balance_interval = 128
		 846 balance_interval = 64
		  55 balance_interval = 63
		 215 balance_interval = 32
		   2 balance_interval = 31
		   2 balance_interval = 16
		   4 balance_interval = 8
		1870 balance_interval = 4
		  65 balance_interval = 2

	MASK=1

		  27 balance_interval = 175
		  37 balance_interval = 127
		 840 balance_interval = 64
		 167 balance_interval = 63
		 449 balance_interval = 32
		  84 balance_interval = 31
		 304 balance_interval = 16
		1156 balance_interval = 8
		2781 balance_interval = 4
		 428 balance_interval = 2

	MASK=f

		   1 balance_interval = 175
		1328 balance_interval = 128
		  44 balance_interval = 64
		 101 balance_interval = 63
		  25 balance_interval = 32
		   5 balance_interval = 31
		  23 balance_interval = 16
		  23 balance_interval = 8
		4306 balance_interval = 4
		 177 balance_interval = 2

AFTER
-----

Note how the high values almost disappear for all MASK values. The
system has background tasks that could trigger the problem without
simulate it even with MASK=0.

	MASK=0

		 103 balance_interval = 63
		  19 balance_interval = 31
		 194 balance_interval = 8
		4827 balance_interval = 4
		 179 balance_interval = 2

	MASK=1

		 131 balance_interval = 63
		   1 balance_interval = 31
		  87 balance_interval = 8
		3600 balance_interval = 4
		   7 balance_interval = 2

	MASK=f

		   8 balance_interval = 127
		 182 balance_interval = 63
		   3 balance_interval = 31
		   9 balance_interval = 16
		 415 balance_interval = 8
		3415 balance_interval = 4
		  21 balance_interval = 2

Signed-off-by: Qais Yousef <qyousef@layalina.io>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20240324004552.999936-3-qyousef@layalina.io
2024-03-25 12:09:54 +01:00

220 lines
6.2 KiB
C
Raw Blame History

// SPDX-License-Identifier: GPL-2.0
#include <linux/init_task.h>
#include <linux/export.h>
#include <linux/mqueue.h>
#include <linux/sched.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/rt.h>
#include <linux/sched/task.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/audit.h>
#include <linux/numa.h>
#include <linux/scs.h>
#include <linux/plist.h>
#include <linux/uaccess.h>
static struct signal_struct init_signals = {
.nr_threads = 1,
.thread_head = LIST_HEAD_INIT(init_task.thread_node),
.wait_chldexit = __WAIT_QUEUE_HEAD_INITIALIZER(init_signals.wait_chldexit),
.shared_pending = {
.list = LIST_HEAD_INIT(init_signals.shared_pending.list),
.signal = {{0}}
},
.multiprocess = HLIST_HEAD_INIT,
.rlim = INIT_RLIMITS,
.cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex),
.exec_update_lock = __RWSEM_INITIALIZER(init_signals.exec_update_lock),
#ifdef CONFIG_POSIX_TIMERS
.posix_timers = LIST_HEAD_INIT(init_signals.posix_timers),
.cputimer = {
.cputime_atomic = INIT_CPUTIME_ATOMIC,
},
#endif
INIT_CPU_TIMERS(init_signals)
.pids = {
[PIDTYPE_PID] = &init_struct_pid,
[PIDTYPE_TGID] = &init_struct_pid,
[PIDTYPE_PGID] = &init_struct_pid,
[PIDTYPE_SID] = &init_struct_pid,
},
INIT_PREV_CPUTIME(init_signals)
};
static struct sighand_struct init_sighand = {
.count = REFCOUNT_INIT(1),
.action = { { { .sa_handler = SIG_DFL, } }, },
.siglock = __SPIN_LOCK_UNLOCKED(init_sighand.siglock),
.signalfd_wqh = __WAIT_QUEUE_HEAD_INITIALIZER(init_sighand.signalfd_wqh),
};
#ifdef CONFIG_SHADOW_CALL_STACK
unsigned long init_shadow_call_stack[SCS_SIZE / sizeof(long)] = {
[(SCS_SIZE / sizeof(long)) - 1] = SCS_END_MAGIC
};
#endif
/*
* Set up the first task table, touch at your own risk!. Base=0,
* limit=0x1fffff (=2MB)
*/
struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
#ifdef CONFIG_THREAD_INFO_IN_TASK
.thread_info = INIT_THREAD_INFO(init_task),
.stack_refcount = REFCOUNT_INIT(1),
#endif
.__state = 0,
.stack = init_stack,
.usage = REFCOUNT_INIT(2),
.flags = PF_KTHREAD,
.prio = MAX_PRIO - 20,
.static_prio = MAX_PRIO - 20,
.normal_prio = MAX_PRIO - 20,
.policy = SCHED_NORMAL,
.cpus_ptr = &init_task.cpus_mask,
.user_cpus_ptr = NULL,
.cpus_mask = CPU_MASK_ALL,
.max_allowed_capacity = SCHED_CAPACITY_SCALE,
.nr_cpus_allowed= NR_CPUS,
.mm = NULL,
.active_mm = &init_mm,
.faults_disabled_mapping = NULL,
.restart_block = {
.fn = do_no_restart_syscall,
},
.se = {
.group_node = LIST_HEAD_INIT(init_task.se.group_node),
},
.rt = {
.run_list = LIST_HEAD_INIT(init_task.rt.run_list),
.time_slice = RR_TIMESLICE,
},
.tasks = LIST_HEAD_INIT(init_task.tasks),
#ifdef CONFIG_SMP
.pushable_tasks = PLIST_NODE_INIT(init_task.pushable_tasks, MAX_PRIO),
#endif
#ifdef CONFIG_CGROUP_SCHED
.sched_task_group = &root_task_group,
#endif
.ptraced = LIST_HEAD_INIT(init_task.ptraced),
.ptrace_entry = LIST_HEAD_INIT(init_task.ptrace_entry),
.real_parent = &init_task,
.parent = &init_task,
.children = LIST_HEAD_INIT(init_task.children),
.sibling = LIST_HEAD_INIT(init_task.sibling),
.group_leader = &init_task,
RCU_POINTER_INITIALIZER(real_cred, &init_cred),
RCU_POINTER_INITIALIZER(cred, &init_cred),
.comm = INIT_TASK_COMM,
.thread = INIT_THREAD,
.fs = &init_fs,
.files = &init_files,
#ifdef CONFIG_IO_URING
.io_uring = NULL,
#endif
.signal = &init_signals,
.sighand = &init_sighand,
.nsproxy = &init_nsproxy,
.pending = {
.list = LIST_HEAD_INIT(init_task.pending.list),
.signal = {{0}}
},
.blocked = {{0}},
.alloc_lock = __SPIN_LOCK_UNLOCKED(init_task.alloc_lock),
.journal_info = NULL,
INIT_CPU_TIMERS(init_task)
.pi_lock = __RAW_SPIN_LOCK_UNLOCKED(init_task.pi_lock),
.timer_slack_ns = 50000, /* 50 usec default slack */
.thread_pid = &init_struct_pid,
.thread_node = LIST_HEAD_INIT(init_signals.thread_head),
#ifdef CONFIG_AUDIT
.loginuid = INVALID_UID,
.sessionid = AUDIT_SID_UNSET,
#endif
#ifdef CONFIG_PERF_EVENTS
.perf_event_mutex = __MUTEX_INITIALIZER(init_task.perf_event_mutex),
.perf_event_list = LIST_HEAD_INIT(init_task.perf_event_list),
#endif
#ifdef CONFIG_PREEMPT_RCU
.rcu_read_lock_nesting = 0,
.rcu_read_unlock_special.s = 0,
.rcu_node_entry = LIST_HEAD_INIT(init_task.rcu_node_entry),
.rcu_blocked_node = NULL,
#endif
#ifdef CONFIG_TASKS_RCU
.rcu_tasks_holdout = false,
.rcu_tasks_holdout_list = LIST_HEAD_INIT(init_task.rcu_tasks_holdout_list),
.rcu_tasks_idle_cpu = -1,
.rcu_tasks_exit_list = LIST_HEAD_INIT(init_task.rcu_tasks_exit_list),
#endif
#ifdef CONFIG_TASKS_TRACE_RCU
.trc_reader_nesting = 0,
.trc_reader_special.s = 0,
.trc_holdout_list = LIST_HEAD_INIT(init_task.trc_holdout_list),
.trc_blkd_node = LIST_HEAD_INIT(init_task.trc_blkd_node),
#endif
#ifdef CONFIG_CPUSETS
.mems_allowed_seq = SEQCNT_SPINLOCK_ZERO(init_task.mems_allowed_seq,
&init_task.alloc_lock),
#endif
#ifdef CONFIG_RT_MUTEXES
.pi_waiters = RB_ROOT_CACHED,
.pi_top_task = NULL,
#endif
INIT_PREV_CPUTIME(init_task)
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
.vtime.seqcount = SEQCNT_ZERO(init_task.vtime_seqcount),
.vtime.starttime = 0,
.vtime.state = VTIME_SYS,
#endif
#ifdef CONFIG_NUMA_BALANCING
.numa_preferred_nid = NUMA_NO_NODE,
.numa_group = NULL,
.numa_faults = NULL,
#endif
#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
.kasan_depth = 1,
#endif
#ifdef CONFIG_KCSAN
.kcsan_ctx = {
.scoped_accesses = {LIST_POISON1, NULL},
},
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
.softirqs_enabled = 1,
#endif
#ifdef CONFIG_LOCKDEP
.lockdep_depth = 0, /* no locks held yet */
.curr_chain_key = INITIAL_CHAIN_KEY,
.lockdep_recursion = 0,
#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
.ret_stack = NULL,
.tracing_graph_pause = ATOMIC_INIT(0),
#endif
#if defined(CONFIG_TRACING) && defined(CONFIG_PREEMPTION)
.trace_recursion = 0,
#endif
#ifdef CONFIG_LIVEPATCH
.patch_state = KLP_UNDEFINED,
#endif
#ifdef CONFIG_SECURITY
.security = NULL,
#endif
#ifdef CONFIG_SECCOMP_FILTER
.seccomp = { .filter_count = ATOMIC_INIT(0) },
#endif
};
EXPORT_SYMBOL(init_task);
/*
* Initial thread structure. Alignment of this is handled by a special
* linker map entry.
*/
#ifndef CONFIG_THREAD_INFO_IN_TASK
struct thread_info init_thread_info __init_thread_info = INIT_THREAD_INFO(init_task);
#endif
Reference in a new issue View git blame Copy permalink