blob: dac02a6219b1cae3c657512b293b957627cec830 [file] [log] [blame]
Paul E. McKenneya241ec62005-10-30 15:03:12 -08001RCU Torture Test Operation
2
3
4CONFIG_RCU_TORTURE_TEST
5
6The CONFIG_RCU_TORTURE_TEST config option is available for all RCU
7implementations. It creates an rcutorture kernel module that can
8be loaded to run a torture test. The test periodically outputs
9status messages via printk(), which can be examined via the dmesg
Paul E. McKenney72e9bb52006-06-27 02:54:03 -070010command (perhaps grepping for "torture"). The test is started
Paul E. McKenneya241ec62005-10-30 15:03:12 -080011when the module is loaded, and stops when the module is unloaded.
12
Paul E. McKenney31a72bc2008-06-18 09:26:49 -070013CONFIG_RCU_TORTURE_TEST_RUNNABLE
14
15It is also possible to specify CONFIG_RCU_TORTURE_TEST=y, which will
16result in the tests being loaded into the base kernel. In this case,
17the CONFIG_RCU_TORTURE_TEST_RUNNABLE config option is used to specify
18whether the RCU torture tests are to be started immediately during
19boot or whether the /proc/sys/kernel/rcutorture_runnable file is used
20to enable them. This /proc file can be used to repeatedly pause and
21restart the tests, regardless of the initial state specified by the
22CONFIG_RCU_TORTURE_TEST_RUNNABLE config option.
23
24You will normally -not- want to start the RCU torture tests during boot
25(and thus the default is CONFIG_RCU_TORTURE_TEST_RUNNABLE=n), but doing
26this can sometimes be useful in finding boot-time bugs.
Paul E. McKenneya241ec62005-10-30 15:03:12 -080027
28
29MODULE PARAMETERS
30
31This module has the following parameters:
32
Paul E. McKenney4c540052010-01-14 16:10:57 -080033fqs_duration Duration (in microseconds) of artificially induced bursts
34 of force_quiescent_state() invocations. In RCU
35 implementations having force_quiescent_state(), these
36 bursts help force races between forcing a given grace
37 period and that grace period ending on its own.
38
39fqs_holdoff Holdoff time (in microseconds) between consecutive calls
40 to force_quiescent_state() within a burst.
41
42fqs_stutter Wait time (in seconds) between consecutive bursts
43 of calls to force_quiescent_state().
44
Paul E. McKenney2ec1f2d2013-06-12 15:12:21 -070045gp_normal Make the fake writers use normal synchronous grace-period
46 primitives.
47
48gp_exp Make the fake writers use expedited synchronous grace-period
49 primitives. If both gp_normal and gp_exp are set, or
50 if neither gp_normal nor gp_exp are set, then randomly
51 choose the primitive so that about 50% are normal and
52 50% expedited. By default, neither are set, which
53 gives best overall test coverage.
54
Paul E. McKenney63cd7582011-06-05 10:07:18 -070055irqreader Says to invoke RCU readers from irq level. This is currently
Paul E. McKenney0729fbf2008-06-25 12:24:52 -070056 done via timers. Defaults to "1" for variants of RCU that
57 permit this. (Or, more accurately, variants of RCU that do
58 -not- permit this know to ignore this variable.)
Paul E. McKenneya241ec62005-10-30 15:03:12 -080059
Paul E. McKenneyfae4b542012-02-20 17:51:45 -080060n_barrier_cbs If this is nonzero, RCU barrier testing will be conducted,
61 in which case n_barrier_cbs specifies the number of
62 RCU callbacks (and corresponding kthreads) to use for
63 this testing. The value cannot be negative. If you
64 specify this to be non-zero when torture_type indicates a
65 synchronous RCU implementation (one for which a member of
66 the synchronize_rcu() rather than the call_rcu() family is
67 used -- see the documentation for torture_type below), an
68 error will be reported and no testing will be carried out.
69
Josh Triplettb772e1d2006-10-04 02:17:13 -070070nfakewriters This is the number of RCU fake writer threads to run. Fake
71 writer threads repeatedly use the synchronous "wait for
72 current readers" function of the interface selected by
73 torture_type, with a delay between calls to allow for various
74 different numbers of writers running in parallel.
75 nfakewriters defaults to 4, which provides enough parallelism
76 to trigger special cases caused by multiple writers, such as
77 the synchronize_srcu() early return optimization.
78
Paul E. McKenney0729fbf2008-06-25 12:24:52 -070079nreaders This is the number of RCU reading threads supported.
80 The default is twice the number of CPUs. Why twice?
81 To properly exercise RCU implementations with preemptible
82 read-side critical sections.
83
Paul E. McKenneyb58bdcc2011-11-16 17:48:21 -080084onoff_interval
85 The number of seconds between each attempt to execute a
86 randomly selected CPU-hotplug operation. Defaults to
87 zero, which disables CPU hotplugging. In HOTPLUG_CPU=n
88 kernels, rcutorture will silently refuse to do any
89 CPU-hotplug operations regardless of what value is
90 specified for onoff_interval.
91
Paul E. McKenney9b9ec9b2012-01-17 14:36:51 -080092onoff_holdoff The number of seconds to wait until starting CPU-hotplug
93 operations. This would normally only be used when
94 rcutorture was built into the kernel and started
95 automatically at boot time, in which case it is useful
96 in order to avoid confusing boot-time code with CPUs
97 coming and going.
98
Paul E. McKenney0729fbf2008-06-25 12:24:52 -070099shuffle_interval
100 The number of seconds to keep the test threads affinitied
101 to a particular subset of the CPUs, defaults to 3 seconds.
102 Used in conjunction with test_no_idle_hz.
103
Paul E. McKenneyd5f546d2011-11-04 11:44:12 -0700104shutdown_secs The number of seconds to run the test before terminating
105 the test and powering off the system. The default is
106 zero, which disables test termination and system shutdown.
107 This capability is useful for automated testing.
108
Paul E. McKenneyc13f3752012-01-20 15:36:33 -0800109stall_cpu The number of seconds that a CPU should be stalled while
110 within both an rcu_read_lock() and a preempt_disable().
111 This stall happens only once per rcutorture run.
112 If you need multiple stalls, use modprobe and rmmod to
113 repeatedly run rcutorture. The default for stall_cpu
114 is zero, which prevents rcutorture from stalling a CPU.
115
116 Note that attempts to rmmod rcutorture while the stall
117 is ongoing will hang, so be careful what value you
118 choose for this module parameter! In addition, too-large
119 values for stall_cpu might well induce failures and
120 warnings in other parts of the kernel. You have been
121 warned!
122
123stall_cpu_holdoff
124 The number of seconds to wait after rcutorture starts
125 before stalling a CPU. Defaults to 10 seconds.
126
Paul E. McKenneya241ec62005-10-30 15:03:12 -0800127stat_interval The number of seconds between output of torture
128 statistics (via printk()). Regardless of the interval,
129 statistics are printed when the module is unloaded.
130 Setting the interval to zero causes the statistics to
131 be printed -only- when the module is unloaded, and this
132 is the default.
133
Paul E. McKenneyd120f652008-06-18 05:21:44 -0700134stutter The length of time to run the test before pausing for this
135 same period of time. Defaults to "stutter=5", so as
136 to run and pause for (roughly) five-second intervals.
137 Specifying "stutter=0" causes the test to run continuously
138 without pausing, which is the old default behavior.
139
Paul E. McKenney63cd7582011-06-05 10:07:18 -0700140test_boost Whether or not to test the ability of RCU to do priority
141 boosting. Defaults to "test_boost=1", which performs
142 RCU priority-inversion testing only if the selected
143 RCU implementation supports priority boosting. Specifying
144 "test_boost=0" never performs RCU priority-inversion
145 testing. Specifying "test_boost=2" performs RCU
146 priority-inversion testing even if the selected RCU
147 implementation does not support RCU priority boosting,
148 which can be used to test rcutorture's ability to
149 carry out RCU priority-inversion testing.
150
151test_boost_interval
152 The number of seconds in an RCU priority-inversion test
153 cycle. Defaults to "test_boost_interval=7". It is
154 usually wise for this value to be relatively prime to
155 the value selected for "stutter".
156
157test_boost_duration
158 The number of seconds to do RCU priority-inversion testing
159 within any given "test_boost_interval". Defaults to
160 "test_boost_duration=4".
161
Paul E. McKenney29766f12006-06-27 02:54:02 -0700162test_no_idle_hz Whether or not to test the ability of RCU to operate in
163 a kernel that disables the scheduling-clock interrupt to
164 idle CPUs. Boolean parameter, "1" to test, "0" otherwise.
Paul E. McKenneyf85d6c72008-01-25 21:08:25 +0100165 Defaults to omitting this test.
Paul E. McKenney29766f12006-06-27 02:54:02 -0700166
Paul E. McKenney63cd7582011-06-05 10:07:18 -0700167torture_type The type of RCU to test, with string values as follows:
168
169 "rcu": rcu_read_lock(), rcu_read_unlock() and call_rcu().
170
171 "rcu_sync": rcu_read_lock(), rcu_read_unlock(), and
172 synchronize_rcu().
173
174 "rcu_expedited": rcu_read_lock(), rcu_read_unlock(), and
175 synchronize_rcu_expedited().
176
177 "rcu_bh": rcu_read_lock_bh(), rcu_read_unlock_bh(), and
178 call_rcu_bh().
179
180 "rcu_bh_sync": rcu_read_lock_bh(), rcu_read_unlock_bh(),
181 and synchronize_rcu_bh().
182
Paul E. McKenneybdf2a432011-06-07 16:59:35 -0700183 "rcu_bh_expedited": rcu_read_lock_bh(), rcu_read_unlock_bh(),
184 and synchronize_rcu_bh_expedited().
185
Paul E. McKenney63cd7582011-06-05 10:07:18 -0700186 "srcu": srcu_read_lock(), srcu_read_unlock() and
Paul E. McKenney74d874e2012-05-07 13:43:30 -0700187 call_srcu().
188
189 "srcu_sync": srcu_read_lock(), srcu_read_unlock() and
Paul E. McKenney63cd7582011-06-05 10:07:18 -0700190 synchronize_srcu().
191
192 "srcu_expedited": srcu_read_lock(), srcu_read_unlock() and
193 synchronize_srcu_expedited().
194
195 "sched": preempt_disable(), preempt_enable(), and
196 call_rcu_sched().
197
198 "sched_sync": preempt_disable(), preempt_enable(), and
199 synchronize_sched().
200
201 "sched_expedited": preempt_disable(), preempt_enable(), and
202 synchronize_sched_expedited().
203
204 Defaults to "rcu".
Paul E. McKenney72e9bb52006-06-27 02:54:03 -0700205
Paul E. McKenneya241ec62005-10-30 15:03:12 -0800206verbose Enable debug printk()s. Default is disabled.
207
208
209OUTPUT
210
211The statistics output is as follows:
212
Paul E. McKenney63cd7582011-06-05 10:07:18 -0700213 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
Paul E. McKenneyfae4b542012-02-20 17:51:45 -0800214 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
Paul E. McKenney63cd7582011-06-05 10:07:18 -0700215 rcu-torture: Reader Pipe: 727860534 34213 0 0 0 0 0 0 0 0 0
216 rcu-torture: Reader Batch: 727877838 17003 0 0 0 0 0 0 0 0 0
217 rcu-torture: Free-Block Circulation: 155440 155440 155440 155440 155440 155440 155440 155440 155440 155440 0
218 rcu-torture:--- End of test: SUCCESS: 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
Paul E. McKenneya241ec62005-10-30 15:03:12 -0800219
Paul E. McKenney72e9bb52006-06-27 02:54:03 -0700220The command "dmesg | grep torture:" will extract this information on
Paul E. McKenneya241ec62005-10-30 15:03:12 -0800221most systems. On more esoteric configurations, it may be necessary to
222use other commands to access the output of the printk()s used by
223the RCU torture test. The printk()s use KERN_ALERT, so they should
224be evident. ;-)
225
Paul E. McKenney63cd7582011-06-05 10:07:18 -0700226The first and last lines show the rcutorture module parameters, and the
227last line shows either "SUCCESS" or "FAILURE", based on rcutorture's
228automatic determination as to whether RCU operated correctly.
229
Paul E. McKenneya241ec62005-10-30 15:03:12 -0800230The entries are as follows:
231
Paul E. McKenneya241ec62005-10-30 15:03:12 -0800232o "rtc": The hexadecimal address of the structure currently visible
233 to readers.
234
Paul E. McKenney63cd7582011-06-05 10:07:18 -0700235o "ver": The number of times since boot that the RCU writer task
Paul E. McKenneya241ec62005-10-30 15:03:12 -0800236 has changed the structure visible to readers.
237
238o "tfle": If non-zero, indicates that the "torture freelist"
Paul E. McKenney63cd7582011-06-05 10:07:18 -0700239 containing structures to be placed into the "rtc" area is empty.
Paul E. McKenneya241ec62005-10-30 15:03:12 -0800240 This condition is important, since it can fool you into thinking
241 that RCU is working when it is not. :-/
242
243o "rta": Number of structures allocated from the torture freelist.
244
245o "rtaf": Number of allocations from the torture freelist that have
Paul E. McKenney63cd7582011-06-05 10:07:18 -0700246 failed due to the list being empty. It is not unusual for this
247 to be non-zero, but it is bad for it to be a large fraction of
248 the value indicated by "rta".
Paul E. McKenneya241ec62005-10-30 15:03:12 -0800249
250o "rtf": Number of frees into the torture freelist.
251
Paul E. McKenney63cd7582011-06-05 10:07:18 -0700252o "rtmbe": A non-zero value indicates that rcutorture believes that
253 rcu_assign_pointer() and rcu_dereference() are not working
254 correctly. This value should be zero.
255
Paul E. McKenneyfae4b542012-02-20 17:51:45 -0800256o "rtbe": A non-zero value indicates that one of the rcu_barrier()
257 family of functions is not working correctly.
258
Paul E. McKenney63cd7582011-06-05 10:07:18 -0700259o "rtbke": rcutorture was unable to create the real-time kthreads
260 used to force RCU priority inversion. This value should be zero.
261
262o "rtbre": Although rcutorture successfully created the kthreads
263 used to force RCU priority inversion, it was unable to set them
264 to the real-time priority level of 1. This value should be zero.
265
266o "rtbf": The number of times that RCU priority boosting failed
267 to resolve RCU priority inversion.
268
269o "rtb": The number of times that rcutorture attempted to force
270 an RCU priority inversion condition. If you are testing RCU
271 priority boosting via the "test_boost" module parameter, this
272 value should be non-zero.
273
274o "nt": The number of times rcutorture ran RCU read-side code from
275 within a timer handler. This value should be non-zero only
276 if you specified the "irqreader" module parameter.
277
Paul E. McKenneya241ec62005-10-30 15:03:12 -0800278o "Reader Pipe": Histogram of "ages" of structures seen by readers.
279 If any entries past the first two are non-zero, RCU is broken.
280 And rcutorture prints the error flag string "!!!" to make sure
281 you notice. The age of a newly allocated structure is zero,
282 it becomes one when removed from reader visibility, and is
283 incremented once per grace period subsequently -- and is freed
284 after passing through (RCU_TORTURE_PIPE_LEN-2) grace periods.
285
286 The output displayed above was taken from a correctly working
287 RCU. If you want to see what it looks like when broken, break
288 it yourself. ;-)
289
290o "Reader Batch": Another histogram of "ages" of structures seen
291 by readers, but in terms of counter flips (or batches) rather
292 than in terms of grace periods. The legal number of non-zero
Paul E. McKenneyf85d6c72008-01-25 21:08:25 +0100293 entries is again two. The reason for this separate view is that
294 it is sometimes easier to get the third entry to show up in the
Paul E. McKenneya241ec62005-10-30 15:03:12 -0800295 "Reader Batch" list than in the "Reader Pipe" list.
296
297o "Free-Block Circulation": Shows the number of torture structures
298 that have reached a given point in the pipeline. The first element
299 should closely correspond to the number of structures allocated,
300 the second to the number that have been removed from reader view,
301 and all but the last remaining to the corresponding number of
302 passes through a grace period. The last entry should be zero,
303 as it is only incremented if a torture structure's counter
304 somehow gets incremented farther than it should.
305
Paul E. McKenneyb2896d22006-10-04 02:17:03 -0700306Different implementations of RCU can provide implementation-specific
Paul E. McKenney63cd7582011-06-05 10:07:18 -0700307additional information. For example, SRCU provides the following
308additional line:
Paul E. McKenneyb2896d22006-10-04 02:17:03 -0700309
Paul E. McKenneyb2896d22006-10-04 02:17:03 -0700310 srcu-torture: per-CPU(idx=1): 0(0,1) 1(0,1) 2(0,0) 3(0,1)
311
Paul E. McKenney63cd7582011-06-05 10:07:18 -0700312This line shows the per-CPU counter state. The numbers in parentheses are
313the values of the "old" and "current" counters for the corresponding CPU.
314The "idx" value maps the "old" and "current" values to the underlying
315array, and is useful for debugging.
Paul E. McKenney240ebbf2009-06-25 09:08:18 -0700316
Paul E. McKenneya241ec62005-10-30 15:03:12 -0800317
318USAGE
319
320The following script may be used to torture RCU:
321
322 #!/bin/sh
323
324 modprobe rcutorture
Paul E. McKenney105617d2012-02-02 11:27:02 -0800325 sleep 3600
Paul E. McKenneya241ec62005-10-30 15:03:12 -0800326 rmmod rcutorture
Paul E. McKenney72e9bb52006-06-27 02:54:03 -0700327 dmesg | grep torture:
Paul E. McKenneya241ec62005-10-30 15:03:12 -0800328
329The output can be manually inspected for the error flag of "!!!".
330One could of course create a more elaborate script that automatically
Paul E. McKenney9b9ec9b2012-01-17 14:36:51 -0800331checked for such errors. The "rmmod" command forces a "SUCCESS",
332"FAILURE", or "RCU_HOTPLUG" indication to be printk()ed. The first
333two are self-explanatory, while the last indicates that while there
334were no RCU failures, CPU-hotplug problems were detected.