multithreading - Linux - Difference between migrations and switches? -

by looking @ scheduling stats in /proc/<pid>/sched, can output this:

[horro@system ~]$ cat /proc/1/sched systemd (1, #threads: 1) ------------------------------------------------------------------- se.exec_start                                :    2499611106.982616 se.vruntime                                  :          7952.917943 se.sum_exec_runtime                          :         58651.279127 se.nr_migrations                             :                53355 nr_switches                                  :               169561 nr_voluntary_switches                        :               168185 nr_involuntary_switches                      :                 1376 se.load.weight                               :              1048576 se.avg.load_sum                              :               343837 se.avg.util_sum                              :               338827 se.avg.load_avg                              :                    7 se.avg.util_avg                              :                    7 se.avg.last_update_time                      :     2499611106982616 policy                                       :                    0 prio                                         :                  120 clock-delta                                  :                  180 mm->numa_scan_seq                            :                    1 numa_pages_migrated                          :                  296 numa_preferred_nid                           :                    0 total_numa_faults                            :                   34 current_node=0, numa_group_id=0 numa_faults node=0 task_private=0 task_shared=23 group_private=0 group_shared=0 numa_faults node=1 task_private=0 task_shared=0 group_private=0 group_shared=0 numa_faults node=2 task_private=0 task_shared=0 group_private=0 group_shared=0 numa_faults node=3 task_private=0 task_shared=11 group_private=0 group_shared=0 numa_faults node=4 task_private=0 task_shared=0 group_private=0 group_shared=0 numa_faults node=5 task_private=0 task_shared=0 group_private=0 group_shared=0 numa_faults node=6 task_private=0 task_shared=0 group_private=0 group_shared=0 numa_faults node=7 task_private=0 task_shared=0 group_private=0 group_shared=0 

i have been trying figure out differences between migrations , switches, responses here , here. summarizing these responses:

• nr_switches: number of context switches.
• nr_voluntary_switches: number of voluntary switches, i.e. thread blocked , hence thread picked up.
• nr_involuntary_switches: scheduler kicked thread out there hungry thread ready run.

therefore, migrations? these concepts related or not? migrations among cores , switches within core?

migration when thread, after context switch, scheduled on different cpu scheduled before.

edit 1:

here more info on wikipedia migration: https://en.wikipedia.org/wiki/process_migration

here kernel code increasing counter: https://github.com/torvalds/linux/blob/master/kernel/sched/core.c#l1175

if (task_cpu(p) != new_cpu) {     ...     p->se.nr_migrations++; 

edit 2:

a thread can migrate cpu in following cases:

1. during exec()
2. during fork()
3. during thread wake-up.
4. if thread affinity mask has changed.
5. when current cpu getting offline.

for more info please have @ functions set_task_cpu(), move_queued_task(), migrate_tasks() in same source file: https://github.com/torvalds/linux/blob/master/kernel/sched/core.c

the policies scheduler follows described in select_task_rq(), depend on class of scheduler using. basic version of policier:

if (p->nr_cpus_allowed > 1)     cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); else     cpu = cpumask_any(&p->cpus_allowed); 

source: https://github.com/torvalds/linux/blob/master/kernel/sched/core.c#l1534

so in order avoid migration, set cpu affinity mask threads using sched_setaffinity(2) system call or corresponding posix api pthread_setaffinity_np(3).

here definition of select_task_rq() fair scheduler: https://github.com/torvalds/linux/blob/master/kernel/sched/fair.c#l5860

the logic quite complicated, basically, either select sibling idle cpu or find least busy new one.

hope answers question.