Linux kernel mirror (for testing)
git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel
os
linux
selftests/rseq: Add rseq slice histogram script
A script that processes trace-cmd data and generates a histogram of
rseq slice_ext durations for the recorded workload.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260121143208.340549136@infradead.org
+135
+3
Documentation/userspace-api/rseq.rst
+3
Documentation/userspace-api/rseq.rst
···
83
83
is the minimum value. It can be incremented to 50 usecs, however doing so
84
84
can/will affect the minimum scheduling latency.
85
85
86
+
Any proposed changes to this default will have to come with a selftest and
87
+
rseq-slice-hist.py output that shows the new value has merrit.
88
+
86
89
The kernel indicates the grant by clearing rseq::slice_ctrl::request and
87
90
setting rseq::slice_ctrl::granted to 1. If there is a reschedule of the
88
91
thread after granting the extension, the kernel clears the granted bit to
+132
tools/testing/selftests/rseq/rseq-slice-hist.py
+132
tools/testing/selftests/rseq/rseq-slice-hist.py
···
1
+
#!/usr/bin/python3
2
+
3
+
#
4
+
# trace-cmd record -e hrtimer_start -e hrtimer_cancel -e hrtimer_expire_entry -- $cmd
5
+
#
6
+
7
+
from tracecmd import *
8
+
9
+
def load_kallsyms(file_path='/proc/kallsyms'):
10
+
"""
11
+
Parses /proc/kallsyms into a dictionary.
12
+
Returns: { address_int: symbol_name }
13
+
"""
14
+
kallsyms_map = {}
15
+
16
+
try:
17
+
with open(file_path, 'r') as f:
18
+
for line in f:
19
+
# The format is: [address] [type] [name] [module]
20
+
parts = line.split()
21
+
if len(parts) < 3:
22
+
continue
23
+
24
+
addr = int(parts[0], 16)
25
+
name = parts[2]
26
+
27
+
kallsyms_map[addr] = name
28
+
29
+
except PermissionError:
30
+
print(f"Error: Permission denied reading {file_path}. Try running with sudo.")
31
+
except FileNotFoundError:
32
+
print(f"Error: {file_path} not found.")
33
+
34
+
return kallsyms_map
35
+
36
+
ksyms = load_kallsyms()
37
+
38
+
# pending[timer_ptr] = {'ts': timestamp, 'comm': comm}
39
+
pending = {}
40
+
41
+
# histograms[comm][bucket] = count
42
+
histograms = {}
43
+
44
+
class OnlineHarmonicMean:
45
+
def __init__(self):
46
+
self.n = 0 # Count of elements
47
+
self.S = 0.0 # Cumulative sum of reciprocals
48
+
49
+
def update(self, x):
50
+
if x == 0:
51
+
raise ValueError("Harmonic mean is undefined for zero.")
52
+
53
+
self.n += 1
54
+
self.S += 1.0 / x
55
+
return self.n / self.S
56
+
57
+
@property
58
+
def mean(self):
59
+
return self.n / self.S if self.n > 0 else 0
60
+
61
+
ohms = {}
62
+
63
+
def handle_start(record):
64
+
func_name = ksyms[record.num_field("function")]
65
+
if "rseq_slice_expired" in func_name:
66
+
timer_ptr = record.num_field("hrtimer")
67
+
pending[timer_ptr] = {
68
+
'ts': record.ts,
69
+
'comm': record.comm
70
+
}
71
+
return None
72
+
73
+
def handle_cancel(record):
74
+
timer_ptr = record.num_field("hrtimer")
75
+
76
+
if timer_ptr in pending:
77
+
start_data = pending.pop(timer_ptr)
78
+
duration_ns = record.ts - start_data['ts']
79
+
duration_us = duration_ns // 1000
80
+
81
+
comm = start_data['comm']
82
+
83
+
if comm not in ohms:
84
+
ohms[comm] = OnlineHarmonicMean()
85
+
86
+
ohms[comm].update(duration_ns)
87
+
88
+
if comm not in histograms:
89
+
histograms[comm] = {}
90
+
91
+
histograms[comm][duration_us] = histograms[comm].get(duration_us, 0) + 1
92
+
return None
93
+
94
+
def handle_expire(record):
95
+
timer_ptr = record.num_field("hrtimer")
96
+
97
+
if timer_ptr in pending:
98
+
start_data = pending.pop(timer_ptr)
99
+
comm = start_data['comm']
100
+
101
+
if comm not in histograms:
102
+
histograms[comm] = {}
103
+
104
+
# Record -1 bucket for expired (failed to cancel)
105
+
histograms[comm][-1] = histograms[comm].get(-1, 0) + 1
106
+
return None
107
+
108
+
if __name__ == "__main__":
109
+
t = Trace("trace.dat")
110
+
for cpu in range(0, t.cpus):
111
+
ev = t.read_event(cpu)
112
+
while ev:
113
+
if "hrtimer_start" in ev.name:
114
+
handle_start(ev)
115
+
if "hrtimer_cancel" in ev.name:
116
+
handle_cancel(ev)
117
+
if "hrtimer_expire_entry" in ev.name:
118
+
handle_expire(ev)
119
+
120
+
ev = t.read_event(cpu)
121
+
122
+
print("\n" + "="*40)
123
+
print("RSEQ SLICE HISTOGRAM (us)")
124
+
print("="*40)
125
+
for comm, buckets in histograms.items():
126
+
print(f"\nTask: {comm} Mean: {ohms[comm].mean:.3f} ns")
127
+
print(f" {'Latency (us)':<15} | {'Count'}")
128
+
print(f" {'-'*30}")
129
+
# Sort buckets numerically, putting -1 at the top
130
+
for bucket in sorted(buckets.keys()):
131
+
label = "EXPIRED" if bucket == -1 else f"{bucket} us"
132
+
print(f" {label:<15} | {buckets[bucket]}")