8639ecebc9
An unbound workqueue can be served by multiple worker_pools to improve locality. The segmentation is achieved by grouping CPUs into pods. By default, the cache boundaries according to cpus_share_cache() define the CPUs are grouped. Let's a workqueue is allowed to run on all CPUs and the system has two L3 caches. The workqueue would be mapped to two worker_pools each serving one L3 cache domains. While this improves locality, because the pod boundaries are strict, it limits the total bandwidth a given issuer can consume. For example, let's say there is a thread pinned to a CPU issuing enough work items to saturate the whole machine. With the machine segmented into two pods, no matter how many work items it issues, it can only use half of the CPUs on the system. While this limitation has existed for a very long time, it wasn't very pronounced because the affinity grouping used to be always by NUMA nodes. With cache boundaries as the default and support for even finer grained scopes (smt and cpu), it is now an a lot more pressing problem. This patch implements non-strict affinity scope where the pod boundaries aren't enforced strictly. Going back to the previous example, the workqueue would still be mapped to two worker_pools; however, the affinity enforcement would be soft. The workers in both pools would have their cpus_allowed set to the whole machine thus allowing the scheduler to migrate them anywhere on the machine. However, whenever an idle worker is woken up, the workqueue code asks the scheduler to bring back the task within the pod if the worker is outside. ie. work items start executing within its affinity scope but can be migrated outside as the scheduler sees fit. This removes the hard cap on utilization while maintaining the benefits of affinity scopes. After the earlier ->__pod_cpumask changes, the implementation is pretty simple. When non-strict which is the new default: * pool_allowed_cpus() returns @pool->attrs->cpumask instead of ->__pod_cpumask so that the workers are allowed to run on any CPU that the associated workqueues allow. * If the idle worker task's ->wake_cpu is outside the pod, kick_pool() sets the field to a CPU within the pod. This would be the first use of task_struct->wake_cpu outside scheduler proper, so it isn't clear whether this would be acceptable. However, other methods of migrating tasks are significantly more expensive and are likely prohibitively so if we want to do this on every work item. This needs discussion with scheduler folks. There is also a race window where setting ->wake_cpu wouldn't be effective as the target task is still on CPU. However, the window is pretty small and this being a best-effort optimization, it doesn't seem to warrant more complexity at the moment. While the non-strict cache affinity scopes seem to be the best option, the performance picture interacts with the affinity scope and is a bit complicated to fully discuss in this patch, so the behavior is made easily selectable through wqattrs and sysfs and the next patch will add documentation to discuss performance implications. v2: pool->attrs->affn_strict is set to true for per-cpu worker_pools. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org>
178 lines
5.6 KiB
Python
178 lines
5.6 KiB
Python
#!/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[,FLAGS] POOL_ID...
|
|
|
|
NAME name of the workqueue
|
|
TYPE percpu, unbound or ordered
|
|
FLAGS S: strict affinity scope
|
|
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_affn_dfl = prog['wq_affn_dfl']
|
|
wq_affn_names = prog['wq_affn_names']
|
|
|
|
WQ_UNBOUND = prog['WQ_UNBOUND']
|
|
WQ_ORDERED = prog['__WQ_ORDERED']
|
|
WQ_MEM_RECLAIM = prog['WQ_MEM_RECLAIM']
|
|
|
|
WQ_AFFN_CPU = prog['WQ_AFFN_CPU']
|
|
WQ_AFFN_SMT = prog['WQ_AFFN_SMT']
|
|
WQ_AFFN_CACHE = prog['WQ_AFFN_CACHE']
|
|
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('')
|
|
|
|
for affn in [WQ_AFFN_CPU, WQ_AFFN_SMT, WQ_AFFN_CACHE, WQ_AFFN_NUMA, WQ_AFFN_SYSTEM]:
|
|
print('')
|
|
print(f'{wq_affn_names[affn].string_().decode().upper()}{" (default)" if affn == wq_affn_dfl else ""}')
|
|
print_pod_type(wq_pod_types[affn])
|
|
|
|
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(f' pod_cpus={cpumask_str(pool.attrs.__pod_cpumask)}', end='')
|
|
if pool.attrs.affn_strict:
|
|
print(' strict', end='')
|
|
print('')
|
|
|
|
print('')
|
|
print('Workqueue CPU -> pool')
|
|
print('=====================')
|
|
|
|
print('[ workqueue \ type 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='')
|
|
if wq.unbound_attrs.affn_strict:
|
|
print(',S ', end='')
|
|
else:
|
|
print(' ', 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('')
|