1
+ .. SPDX-License-Identifier: GPL-2.0
2
+
3
+ ==========================
1
4
RCU Torture Test Operation
5
+ ==========================
2
6
3
7
4
8
CONFIG_RCU_TORTURE_TEST
9
+ =======================
5
10
6
11
The CONFIG_RCU_TORTURE_TEST config option is available for all RCU
7
12
implementations. It creates an rcutorture kernel module that can
@@ -13,9 +18,10 @@ when the module is loaded, and stops when the module is unloaded.
13
18
Module parameters are prefixed by "rcutorture." in
14
19
Documentation/admin-guide/kernel-parameters.txt.
15
20
16
- OUTPUT
21
+ Output
22
+ ======
17
23
18
- The statistics output is as follows:
24
+ The statistics output is as follows::
19
25
20
26
rcu-torture:--- Start of test: nreaders=16 nfakewriters=4 stat_interval=30 verbose=0 test_no_idle_hz=1 shuffle_interval=3 stutter=5 irqreader=1 fqs_duration=0 fqs_holdoff=0 fqs_stutter=3 test_boost=1/0 test_boost_interval=7 test_boost_duration=4
21
27
rcu-torture: rtc: (null) ver: 155441 tfle: 0 rta: 155441 rtaf: 8884 rtf: 155440 rtmbe: 0 rtbe: 0 rtbke: 0 rtbre: 0 rtbf: 0 rtb: 0 nt: 3055767
@@ -36,53 +42,53 @@ automatic determination as to whether RCU operated correctly.
36
42
37
43
The entries are as follows:
38
44
39
- o "rtc": The hexadecimal address of the structure currently visible
45
+ * "rtc": The hexadecimal address of the structure currently visible
40
46
to readers.
41
47
42
- o "ver": The number of times since boot that the RCU writer task
48
+ * "ver": The number of times since boot that the RCU writer task
43
49
has changed the structure visible to readers.
44
50
45
- o "tfle": If non-zero, indicates that the "torture freelist"
51
+ * "tfle": If non-zero, indicates that the "torture freelist"
46
52
containing structures to be placed into the "rtc" area is empty.
47
53
This condition is important, since it can fool you into thinking
48
54
that RCU is working when it is not. :-/
49
55
50
- o "rta": Number of structures allocated from the torture freelist.
56
+ * "rta": Number of structures allocated from the torture freelist.
51
57
52
- o "rtaf": Number of allocations from the torture freelist that have
58
+ * "rtaf": Number of allocations from the torture freelist that have
53
59
failed due to the list being empty. It is not unusual for this
54
60
to be non-zero, but it is bad for it to be a large fraction of
55
61
the value indicated by "rta".
56
62
57
- o "rtf": Number of frees into the torture freelist.
63
+ * "rtf": Number of frees into the torture freelist.
58
64
59
- o "rtmbe": A non-zero value indicates that rcutorture believes that
65
+ * "rtmbe": A non-zero value indicates that rcutorture believes that
60
66
rcu_assign_pointer() and rcu_dereference() are not working
61
67
correctly. This value should be zero.
62
68
63
- o "rtbe": A non-zero value indicates that one of the rcu_barrier()
69
+ * "rtbe": A non-zero value indicates that one of the rcu_barrier()
64
70
family of functions is not working correctly.
65
71
66
- o "rtbke": rcutorture was unable to create the real-time kthreads
72
+ * "rtbke": rcutorture was unable to create the real-time kthreads
67
73
used to force RCU priority inversion. This value should be zero.
68
74
69
- o "rtbre": Although rcutorture successfully created the kthreads
75
+ * "rtbre": Although rcutorture successfully created the kthreads
70
76
used to force RCU priority inversion, it was unable to set them
71
77
to the real-time priority level of 1. This value should be zero.
72
78
73
- o "rtbf": The number of times that RCU priority boosting failed
79
+ * "rtbf": The number of times that RCU priority boosting failed
74
80
to resolve RCU priority inversion.
75
81
76
- o "rtb": The number of times that rcutorture attempted to force
82
+ * "rtb": The number of times that rcutorture attempted to force
77
83
an RCU priority inversion condition. If you are testing RCU
78
84
priority boosting via the "test_boost" module parameter, this
79
85
value should be non-zero.
80
86
81
- o "nt": The number of times rcutorture ran RCU read-side code from
87
+ * "nt": The number of times rcutorture ran RCU read-side code from
82
88
within a timer handler. This value should be non-zero only
83
89
if you specified the "irqreader" module parameter.
84
90
85
- o "Reader Pipe": Histogram of "ages" of structures seen by readers.
91
+ * "Reader Pipe": Histogram of "ages" of structures seen by readers.
86
92
If any entries past the first two are non-zero, RCU is broken.
87
93
And rcutorture prints the error flag string "!!!" to make sure
88
94
you notice. The age of a newly allocated structure is zero,
@@ -94,14 +100,14 @@ o "Reader Pipe": Histogram of "ages" of structures seen by readers.
94
100
RCU. If you want to see what it looks like when broken, break
95
101
it yourself. ;-)
96
102
97
- o "Reader Batch": Another histogram of "ages" of structures seen
103
+ * "Reader Batch": Another histogram of "ages" of structures seen
98
104
by readers, but in terms of counter flips (or batches) rather
99
105
than in terms of grace periods. The legal number of non-zero
100
106
entries is again two. The reason for this separate view is that
101
107
it is sometimes easier to get the third entry to show up in the
102
108
"Reader Batch" list than in the "Reader Pipe" list.
103
109
104
- o "Free-Block Circulation": Shows the number of torture structures
110
+ * "Free-Block Circulation": Shows the number of torture structures
105
111
that have reached a given point in the pipeline. The first element
106
112
should closely correspond to the number of structures allocated,
107
113
the second to the number that have been removed from reader view,
@@ -112,7 +118,7 @@ o "Free-Block Circulation": Shows the number of torture structures
112
118
113
119
Different implementations of RCU can provide implementation-specific
114
120
additional information. For example, Tree SRCU provides the following
115
- additional line:
121
+ additional line::
116
122
117
123
srcud-torture: Tree SRCU per-CPU(idx=0): 0(35,-21) 1(-4,24) 2(1,1) 3(-26,20) 4(28,-47) 5(-9,4) 6(-10,14) 7(-14,11) T(1,6)
118
124
@@ -123,15 +129,15 @@ using a dynamically allocated srcu_struct (hence "srcud-" rather than
123
129
"old" and "current" values to the underlying array, and is useful for
124
130
debugging. The final "T" entry contains the totals of the counters.
125
131
126
-
127
- USAGE ON SPECIFIC KERNEL BUILDS
132
+ Usage on Specific Kernel Builds
133
+ ===============================
128
134
129
135
It is sometimes desirable to torture RCU on a specific kernel build,
130
136
for example, when preparing to put that kernel build into production.
131
137
In that case, the kernel should be built with CONFIG_RCU_TORTURE_TEST=m
132
138
so that the test can be started using modprobe and terminated using rmmod.
133
139
134
- For example, the following script may be used to torture RCU:
140
+ For example, the following script may be used to torture RCU::
135
141
136
142
#!/bin/sh
137
143
@@ -148,7 +154,8 @@ two are self-explanatory, while the last indicates that while there
148
154
were no RCU failures, CPU-hotplug problems were detected.
149
155
150
156
151
- USAGE ON MAINLINE KERNELS
157
+ Usage on Mainline Kernels
158
+ =========================
152
159
153
160
When using rcutorture to test changes to RCU itself, it is often
154
161
necessary to build a number of kernels in order to test that change
@@ -180,16 +187,16 @@ to Tree SRCU might run only the SRCU-N and SRCU-P scenarios using the
180
187
--configs argument to kvm.sh as follows: "--configs 'SRCU-N SRCU-P'".
181
188
Large systems can run multiple copies of of the full set of scenarios,
182
189
for example, a system with 448 hardware threads can run five instances
183
- of the full set concurrently. To make this happen:
190
+ of the full set concurrently. To make this happen::
184
191
185
192
kvm.sh --cpus 448 --configs '5*CFLIST'
186
193
187
194
Alternatively, such a system can run 56 concurrent instances of a single
188
- eight-CPU scenario:
195
+ eight-CPU scenario::
189
196
190
197
kvm.sh --cpus 448 --configs '56*TREE04'
191
198
192
- Or 28 concurrent instances of each of two eight-CPU scenarios:
199
+ Or 28 concurrent instances of each of two eight-CPU scenarios::
193
200
194
201
kvm.sh --cpus 448 --configs '28*TREE03 28*TREE04'
195
202
@@ -199,14 +206,14 @@ values for memory may require disabling the callback-flooding tests
199
206
using the --bootargs parameter discussed below.
200
207
201
208
Sometimes additional debugging is useful, and in such cases the --kconfig
202
- parameter to kvm.sh may be used, for example, " --kconfig 'CONFIG_KASAN=y'" .
209
+ parameter to kvm.sh may be used, for example, `` --kconfig 'CONFIG_KASAN=y' `` .
203
210
204
211
Kernel boot arguments can also be supplied, for example, to control
205
212
rcutorture's module parameters. For example, to test a change to RCU's
206
213
CPU stall-warning code, use "--bootargs 'rcutorture.stall_cpu=30'".
207
214
This will of course result in the scripting reporting a failure, namely
208
215
the resuling RCU CPU stall warning. As noted above, reducing memory may
209
- require disabling rcutorture's callback-flooding tests:
216
+ require disabling rcutorture's callback-flooding tests::
210
217
211
218
kvm.sh --cpus 448 --configs '56*TREE04' --memory 128M \
212
219
--bootargs 'rcutorture.fwd_progress=0'
@@ -225,7 +232,7 @@ is listed at the end of the kvm.sh output, which you really should redirect
225
232
to a file. The build products and console output of each run is kept in
226
233
tools/testing/selftests/rcutorture/res in timestamped directories. A
227
234
given directory can be supplied to kvm-find-errors.sh in order to have
228
- it cycle you through summaries of errors and full error logs. For example:
235
+ it cycle you through summaries of errors and full error logs. For example::
229
236
230
237
tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh \
231
238
tools/testing/selftests/rcutorture/res/2020.01.20-15.54.23
@@ -245,38 +252,42 @@ that was tested and any uncommitted changes in diff format.
245
252
246
253
The most frequently used files in each per-scenario-run directory are:
247
254
248
- .config: This file contains the Kconfig options.
255
+ .config:
256
+ This file contains the Kconfig options.
249
257
250
- Make.out: This contains build output for a specific scenario.
258
+ Make.out:
259
+ This contains build output for a specific scenario.
251
260
252
- console.log: This contains the console output for a specific scenario.
261
+ console.log:
262
+ This contains the console output for a specific scenario.
253
263
This file may be examined once the kernel has booted, but
254
264
it might not exist if the build failed.
255
265
256
- vmlinux: This contains the kernel, which can be useful with tools like
266
+ vmlinux:
267
+ This contains the kernel, which can be useful with tools like
257
268
objdump and gdb.
258
269
259
270
A number of additional files are available, but are less frequently used.
260
271
Many are intended for debugging of rcutorture itself or of its scripting.
261
272
262
273
As of v5.4, a successful run with the default set of scenarios produces
263
- the following summary at the end of the run on a 12-CPU system:
264
-
265
- SRCU-N ------- 804233 GPs (148.932/s) [srcu: g10008272 f0x0 ]
266
- SRCU-P ------- 202320 GPs (37.4667/s) [srcud: g1809476 f0x0 ]
267
- SRCU-t ------- 1122086 GPs (207.794/s) [srcu: g0 f0x0 ]
268
- SRCU-u ------- 1111285 GPs (205.794/s) [srcud: g1 f0x0 ]
269
- TASKS01 ------- 19666 GPs (3.64185/s) [tasks: g0 f0x0 ]
270
- TASKS02 ------- 20541 GPs (3.80389/s) [tasks: g0 f0x0 ]
271
- TASKS03 ------- 19416 GPs (3.59556/s) [tasks: g0 f0x0 ]
272
- TINY01 ------- 836134 GPs (154.84/s) [rcu: g0 f0x0 ] n_max_cbs: 34198
273
- TINY02 ------- 850371 GPs (157.476/s) [rcu: g0 f0x0 ] n_max_cbs: 2631
274
- TREE01 ------- 162625 GPs (30.1157/s) [rcu: g1124169 f0x0 ]
275
- TREE02 ------- 333003 GPs (61.6672/s) [rcu: g2647753 f0x0 ] n_max_cbs: 35844
276
- TREE03 ------- 306623 GPs (56.782/s) [rcu: g2975325 f0x0 ] n_max_cbs: 1496497
277
- CPU count limited from 16 to 12
278
- TREE04 ------- 246149 GPs (45.5831/s) [rcu: g1695737 f0x0 ] n_max_cbs: 434961
279
- TREE05 ------- 314603 GPs (58.2598/s) [rcu: g2257741 f0x2 ] n_max_cbs: 193997
280
- TREE07 ------- 167347 GPs (30.9902/s) [rcu: g1079021 f0x0 ] n_max_cbs: 478732
281
- CPU count limited from 16 to 12
282
- TREE09 ------- 752238 GPs (139.303/s) [rcu: g13075057 f0x0 ] n_max_cbs: 99011
274
+ the following summary at the end of the run on a 12-CPU system::
275
+
276
+ SRCU-N ------- 804233 GPs (148.932/s) [srcu: g10008272 f0x0 ]
277
+ SRCU-P ------- 202320 GPs (37.4667/s) [srcud: g1809476 f0x0 ]
278
+ SRCU-t ------- 1122086 GPs (207.794/s) [srcu: g0 f0x0 ]
279
+ SRCU-u ------- 1111285 GPs (205.794/s) [srcud: g1 f0x0 ]
280
+ TASKS01 ------- 19666 GPs (3.64185/s) [tasks: g0 f0x0 ]
281
+ TASKS02 ------- 20541 GPs (3.80389/s) [tasks: g0 f0x0 ]
282
+ TASKS03 ------- 19416 GPs (3.59556/s) [tasks: g0 f0x0 ]
283
+ TINY01 ------- 836134 GPs (154.84/s) [rcu: g0 f0x0 ] n_max_cbs: 34198
284
+ TINY02 ------- 850371 GPs (157.476/s) [rcu: g0 f0x0 ] n_max_cbs: 2631
285
+ TREE01 ------- 162625 GPs (30.1157/s) [rcu: g1124169 f0x0 ]
286
+ TREE02 ------- 333003 GPs (61.6672/s) [rcu: g2647753 f0x0 ] n_max_cbs: 35844
287
+ TREE03 ------- 306623 GPs (56.782/s) [rcu: g2975325 f0x0 ] n_max_cbs: 1496497
288
+ CPU count limited from 16 to 12
289
+ TREE04 ------- 246149 GPs (45.5831/s) [rcu: g1695737 f0x0 ] n_max_cbs: 434961
290
+ TREE05 ------- 314603 GPs (58.2598/s) [rcu: g2257741 f0x2 ] n_max_cbs: 193997
291
+ TREE07 ------- 167347 GPs (30.9902/s) [rcu: g1079021 f0x0 ] n_max_cbs: 478732
292
+ CPU count limited from 16 to 12
293
+ TREE09 ------- 752238 GPs (139.303/s) [rcu: g13075057 f0x0 ] n_max_cbs: 99011
0 commit comments