Commit 7f7dc377 authored by Tejun Heo's avatar Tejun Heo
Browse files

workqueue: Add tools/workqueue/wq_dump.py which prints out workqueue configuration 



Lack of visibility has always been a pain point for workqueues. While the
recently added wq_monitor.py improved the situation, it's still difficult to
understand what worker pools are active in the system, how workqueues map to
them and why. The lack of visibility into how workqueues are configured is
going to become more noticeable as workqueue improves locality awareness and
provides more mechanisms to customize locality related behaviors.

Now that the basic framework for more flexible locality support is in place,
this is a good time to improve the situation. This patch adds
tools/workqueues/wq_dump.py which prints out the topology configuration,
worker pools and how workqueues are mapped to pools. Read the command's help
message for more details.

Signed-off-by: default avatarTejun Heo <tj@kernel.org>
parent 84193c07

Documentation/core-api/workqueue.rst

+59 −0
Original line number Diff line number Diff line
@@ -347,6 +347,65 @@ Guidelines 
  level of locality in wq operations and work item execution.





Examining Configuration

=======================



Use tools/workqueue/wq_dump.py to examine unbound CPU affinity

configuration, worker pools and how workqueues map to the pools: ::



  $ tools/workqueue/wq_dump.py

  Affinity Scopes

  ===============

  wq_unbound_cpumask=0000000f



  NUMA

    nr_pods  2

    pod_cpus [0]=00000003 [1]=0000000c

    pod_node [0]=0 [1]=1

    cpu_pod  [0]=0 [1]=0 [2]=1 [3]=1



  SYSTEM

    nr_pods  1

    pod_cpus [0]=0000000f

    pod_node [0]=-1

    cpu_pod  [0]=0 [1]=0 [2]=0 [3]=0



  Worker Pools

  ============

  pool[00] ref= 1 nice=  0 idle/workers=  4/  4 cpu=  0

  pool[01] ref= 1 nice=-20 idle/workers=  2/  2 cpu=  0

  pool[02] ref= 1 nice=  0 idle/workers=  4/  4 cpu=  1

  pool[03] ref= 1 nice=-20 idle/workers=  2/  2 cpu=  1

  pool[04] ref= 1 nice=  0 idle/workers=  4/  4 cpu=  2

  pool[05] ref= 1 nice=-20 idle/workers=  2/  2 cpu=  2

  pool[06] ref= 1 nice=  0 idle/workers=  3/  3 cpu=  3

  pool[07] ref= 1 nice=-20 idle/workers=  2/  2 cpu=  3

  pool[08] ref=42 nice=  0 idle/workers=  6/  6 cpus=0000000f

  pool[09] ref=28 nice=  0 idle/workers=  3/  3 cpus=00000003

  pool[10] ref=28 nice=  0 idle/workers= 17/ 17 cpus=0000000c

  pool[11] ref= 1 nice=-20 idle/workers=  1/  1 cpus=0000000f

  pool[12] ref= 2 nice=-20 idle/workers=  1/  1 cpus=00000003

  pool[13] ref= 2 nice=-20 idle/workers=  1/  1 cpus=0000000c



  Workqueue CPU -> pool

  =====================

  [    workqueue \ CPU              0  1  2  3 dfl]

  events                   percpu   0  2  4  6

  events_highpri           percpu   1  3  5  7

  events_long              percpu   0  2  4  6

  events_unbound           unbound  9  9 10 10  8

  events_freezable         percpu   0  2  4  6

  events_power_efficient   percpu   0  2  4  6

  events_freezable_power_  percpu   0  2  4  6

  rcu_gp                   percpu   0  2  4  6

  rcu_par_gp               percpu   0  2  4  6

  slub_flushwq             percpu   0  2  4  6

  netns                    ordered  8  8  8  8  8

  ...



See the command's help message for more info.





Monitoring

==========

tools/workqueue/wq_dump.py

0 → 100644
+166 −0
Original line number Diff line number Diff line 
#!/usr/bin/env drgn

#

# Copyright (C) 2023 Tejun Heo <tj@kernel.org>

# Copyright (C) 2023 Meta Platforms, Inc. and affiliates.



desc = """

This is a drgn script to show the current workqueue configuration. For more

info on drgn, visit https://github.com/osandov/drgn.



Affinity Scopes

===============



Shows the CPUs that can be used for unbound workqueues and how they will be

grouped by each available affinity type. For each type:



  nr_pods   number of CPU pods in the affinity type

  pod_cpus  CPUs in each pod

  pod_node  NUMA node for memory allocation for each pod

  cpu_pod   pod that each CPU is associated to



Worker Pools

============



Lists all worker pools indexed by their ID. For each pool:



  ref       number of pool_workqueue's associated with this pool

  nice      nice value of the worker threads in the pool

  idle      number of idle workers

  workers   number of all workers

  cpu       CPU the pool is associated with (per-cpu pool)

  cpus      CPUs the workers in the pool can run on (unbound pool)



Workqueue CPU -> pool

=====================



Lists all workqueues along with their type and worker pool association. For

each workqueue:



  NAME TYPE POOL_ID...



  NAME      name of the workqueue

  TYPE      percpu, unbound or ordered

  POOL_ID   worker pool ID associated with each possible CPU

"""



import sys



import drgn

from drgn.helpers.linux.list import list_for_each_entry,list_empty

from drgn.helpers.linux.percpu import per_cpu_ptr

from drgn.helpers.linux.cpumask import for_each_cpu,for_each_possible_cpu

from drgn.helpers.linux.idr import idr_for_each



import argparse

parser = argparse.ArgumentParser(description=desc,

                                 formatter_class=argparse.RawTextHelpFormatter)

args = parser.parse_args()



def err(s):

    print(s, file=sys.stderr, flush=True)

    sys.exit(1)



def cpumask_str(cpumask):

    output = ""

    base = 0

    v = 0

    for cpu in for_each_cpu(cpumask[0]):

        while cpu - base >= 32:

            output += f'{hex(v)} '

            base += 32

            v = 0

        v |= 1 << (cpu - base)

    if v > 0:

        output += f'{v:08x}'

    return output.strip()



worker_pool_idr         = prog['worker_pool_idr']

workqueues              = prog['workqueues']

wq_unbound_cpumask      = prog['wq_unbound_cpumask']

wq_pod_types            = prog['wq_pod_types']



WQ_UNBOUND              = prog['WQ_UNBOUND']

WQ_ORDERED              = prog['__WQ_ORDERED']

WQ_MEM_RECLAIM          = prog['WQ_MEM_RECLAIM']



WQ_AFFN_NUMA            = prog['WQ_AFFN_NUMA']

WQ_AFFN_SYSTEM          = prog['WQ_AFFN_SYSTEM']



print('Affinity Scopes')

print('===============')



print(f'wq_unbound_cpumask={cpumask_str(wq_unbound_cpumask)}')



def print_pod_type(pt):

    print(f'  nr_pods  {pt.nr_pods.value_()}')



    print('  pod_cpus', end='')

    for pod in range(pt.nr_pods):

        print(f' [{pod}]={cpumask_str(pt.pod_cpus[pod])}', end='')

    print('')



    print('  pod_node', end='')

    for pod in range(pt.nr_pods):

        print(f' [{pod}]={pt.pod_node[pod].value_()}', end='')

    print('')



    print(f'  cpu_pod ', end='')

    for cpu in for_each_possible_cpu(prog):

        print(f' [{cpu}]={pt.cpu_pod[cpu].value_()}', end='')

    print('')



print('')

print('NUMA')

print_pod_type(wq_pod_types[WQ_AFFN_NUMA])

print('')

print('SYSTEM')

print_pod_type(wq_pod_types[WQ_AFFN_SYSTEM])



print('')

print('Worker Pools')

print('============')



max_pool_id_len = 0

max_ref_len = 0

for pi, pool in idr_for_each(worker_pool_idr):

    pool = drgn.Object(prog, 'struct worker_pool', address=pool)

    max_pool_id_len = max(max_pool_id_len, len(f'{pi}'))

    max_ref_len = max(max_ref_len, len(f'{pool.refcnt.value_()}'))



for pi, pool in idr_for_each(worker_pool_idr):

    pool = drgn.Object(prog, 'struct worker_pool', address=pool)

    print(f'pool[{pi:0{max_pool_id_len}}] ref={pool.refcnt.value_():{max_ref_len}} nice={pool.attrs.nice.value_():3} ', end='')

    print(f'idle/workers={pool.nr_idle.value_():3}/{pool.nr_workers.value_():3} ', end='')

    if pool.cpu >= 0:

        print(f'cpu={pool.cpu.value_():3}', end='')

    else:

        print(f'cpus={cpumask_str(pool.attrs.cpumask)}', end='')

    print('')



print('')

print('Workqueue CPU -> pool')

print('=====================')



print('[    workqueue \ CPU            ', end='')

for cpu in for_each_possible_cpu(prog):

    print(f' {cpu:{max_pool_id_len}}', end='')

print(' dfl]')



for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'):

    print(f'{wq.name.string_().decode()[-24:]:24}', end='')

    if wq.flags & WQ_UNBOUND:

        if wq.flags & WQ_ORDERED:

            print(' ordered', end='')

        else:

            print(' unbound', end='')

    else:

        print(' percpu ', end='')



    for cpu in for_each_possible_cpu(prog):

        pool_id = per_cpu_ptr(wq.cpu_pwq, cpu)[0].pool.id.value_()

        field_len = max(len(str(cpu)), max_pool_id_len)

        print(f' {pool_id:{field_len}}', end='')



    if wq.flags & WQ_UNBOUND:

        print(f' {wq.dfl_pwq.pool.id.value_():{max_pool_id_len}}', end='')

    print('')