Skip to content
Navigation Menu
Toggle navigation
Sign in
In this repository
All GitHub Enterprise
↵
Jump to
↵
No suggested jump to results
In this repository
All GitHub Enterprise
↵
Jump to
↵
In this organization
All GitHub Enterprise
↵
Jump to
↵
In this repository
All GitHub Enterprise
↵
Jump to
↵
Sign in
Reseting focus
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
mariux64
/
linux
Public
Notifications
You must be signed in to change notification settings
Fork
0
Star
0
Code
Issues
1
Pull requests
0
Actions
Projects
0
Wiki
Security
Insights
Additional navigation options
Code
Issues
Pull requests
Actions
Projects
Wiki
Security
Insights
Files
8639ece
Documentation
LICENSES
arch
block
certs
crypto
drivers
fs
include
init
io_uring
ipc
kernel
lib
mm
net
rust
samples
scripts
security
sound
tools
accounting
arch
bootconfig
bpf
build
certs
cgroup
counter
debugging
edid
firewire
firmware
gpio
hv
iio
include
io_uring
kvm
laptop
leds
lib
memory-model
mm
net
objtool
pci
pcmcia
perf
power
rcu
scripts
spi
testing
thermal
time
tracing
usb
verification
virtio
wmi
workqueue
wq_dump.py
wq_monitor.py
Makefile
usr
virt
.clang-format
.cocciconfig
.get_maintainer.ignore
.gitattributes
.gitignore
.mailmap
.rustfmt.toml
COPYING
CREDITS
Kbuild
Kconfig
MAINTAINERS
Makefile
README
Breadcrumbs
linux
/
tools
/
workqueue
/
wq_monitor.py
Copy path
Blame
Blame
Latest commit
History
History
175 lines (142 loc) · 6.37 KB
Breadcrumbs
linux
/
tools
/
workqueue
/
wq_monitor.py
Top
File metadata and controls
Code
Blame
175 lines (142 loc) · 6.37 KB
Raw
#!/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 monitor workqueues. For more info on drgn, visit https://github.com/osandov/drgn. total Total number of work items executed by the workqueue. infl The number of currently in-flight work items. CPUtime Total CPU time consumed by the workqueue in seconds. This is sampled from scheduler ticks and only provides ballpark measurement. "nohz_full=" CPUs are excluded from measurement. CPUitsv The number of times a concurrency-managed work item hogged CPU longer than the threshold (workqueue.cpu_intensive_thresh_us) and got excluded from concurrency management to avoid stalling other work items. CMW/RPR For per-cpu workqueues, the number of concurrency-management wake-ups while executing a work item of the workqueue. For unbound workqueues, the number of times a worker was repatriated to its affinity scope after being migrated to an off-scope CPU by the scheduler. mayday The number of times the rescuer was requested while waiting for new worker creation. rescued The number of work items executed by the rescuer. """ import sys import signal import os import re import time import json import drgn from drgn.helpers.linux.list import list_for_each_entry,list_empty from drgn.helpers.linux.cpumask import for_each_possible_cpu import argparse parser = argparse.ArgumentParser(description=desc, formatter_class=argparse.RawTextHelpFormatter) parser.add_argument('workqueue', metavar='REGEX', nargs='*', help='Target workqueue name patterns (all if empty)') parser.add_argument('-i', '--interval', metavar='SECS', type=float, default=1, help='Monitoring interval (0 to print once and exit)') parser.add_argument('-j', '--json', action='store_true', help='Output in json') args = parser.parse_args() def err(s): print(s, file=sys.stderr, flush=True) sys.exit(1) workqueues = prog['workqueues'] WQ_UNBOUND = prog['WQ_UNBOUND'] WQ_MEM_RECLAIM = prog['WQ_MEM_RECLAIM'] PWQ_STAT_STARTED = prog['PWQ_STAT_STARTED'] # work items started execution PWQ_STAT_COMPLETED = prog['PWQ_STAT_COMPLETED'] # work items completed execution PWQ_STAT_CPU_TIME = prog['PWQ_STAT_CPU_TIME'] # total CPU time consumed PWQ_STAT_CPU_INTENSIVE = prog['PWQ_STAT_CPU_INTENSIVE'] # wq_cpu_intensive_thresh_us violations PWQ_STAT_CM_WAKEUP = prog['PWQ_STAT_CM_WAKEUP'] # concurrency-management worker wakeups PWQ_STAT_REPATRIATED = prog['PWQ_STAT_REPATRIATED'] # unbound workers brought back into scope PWQ_STAT_MAYDAY = prog['PWQ_STAT_MAYDAY'] # maydays to rescuer PWQ_STAT_RESCUED = prog['PWQ_STAT_RESCUED'] # linked work items executed by rescuer PWQ_NR_STATS = prog['PWQ_NR_STATS'] class WqStats: def __init__(self, wq): self.name = wq.name.string_().decode() self.unbound = wq.flags & WQ_UNBOUND != 0 self.mem_reclaim = wq.flags & WQ_MEM_RECLAIM != 0 self.stats = [0] * PWQ_NR_STATS for pwq in list_for_each_entry('struct pool_workqueue', wq.pwqs.address_of_(), 'pwqs_node'): for i in range(PWQ_NR_STATS): self.stats[i] += int(pwq.stats[i]) def dict(self, now): return { 'timestamp' : now, 'name' : self.name, 'unbound' : self.unbound, 'mem_reclaim' : self.mem_reclaim, 'started' : self.stats[PWQ_STAT_STARTED], 'completed' : self.stats[PWQ_STAT_COMPLETED], 'cpu_time' : self.stats[PWQ_STAT_CPU_TIME], 'cpu_intensive' : self.stats[PWQ_STAT_CPU_INTENSIVE], 'cm_wakeup' : self.stats[PWQ_STAT_CM_WAKEUP], 'repatriated' : self.stats[PWQ_STAT_REPATRIATED], 'mayday' : self.stats[PWQ_STAT_MAYDAY], 'rescued' : self.stats[PWQ_STAT_RESCUED], } def table_header_str(): return f'{"":>24} {"total":>8} {"infl":>5} {"CPUtime":>8} '\ f'{"CPUitsv":>7} {"CMW/RPR":>7} {"mayday":>7} {"rescued":>7}' def table_row_str(self): cpu_intensive = '-' cmw_rpr = '-' mayday = '-' rescued = '-' if self.unbound: cmw_rpr = str(self.stats[PWQ_STAT_REPATRIATED]); else: cpu_intensive = str(self.stats[PWQ_STAT_CPU_INTENSIVE]) cmw_rpr = str(self.stats[PWQ_STAT_CM_WAKEUP]) if self.mem_reclaim: mayday = str(self.stats[PWQ_STAT_MAYDAY]) rescued = str(self.stats[PWQ_STAT_RESCUED]) out = f'{self.name[-24:]:24} ' \ f'{self.stats[PWQ_STAT_STARTED]:8} ' \ f'{max(self.stats[PWQ_STAT_STARTED] - self.stats[PWQ_STAT_COMPLETED], 0):5} ' \ f'{self.stats[PWQ_STAT_CPU_TIME] / 1000000:8.1f} ' \ f'{cpu_intensive:>7} ' \ f'{cmw_rpr:>7} ' \ f'{mayday:>7} ' \ f'{rescued:>7} ' return out.rstrip(':') exit_req = False def sigint_handler(signr, frame): global exit_req exit_req = True def main(): # handle args table_fmt = not args.json interval = args.interval re_str = None if args.workqueue: for r in args.workqueue: if re_str is None: re_str = r else: re_str += '|' + r filter_re = re.compile(re_str) if re_str else None # monitoring loop signal.signal(signal.SIGINT, sigint_handler) while not exit_req: now = time.time() if table_fmt: print() print(WqStats.table_header_str()) for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'): stats = WqStats(wq) if filter_re and not filter_re.search(stats.name): continue if table_fmt: print(stats.table_row_str()) else: print(stats.dict(now)) if interval == 0: break time.sleep(interval) if __name__ == "__main__": main()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
You can’t perform that action at this time.