1 RCU Torture Test Operation
4 CONFIG_RCU_TORTURE_TEST
6 The CONFIG_RCU_TORTURE_TEST config option is available for all RCU
7 implementations. It creates an rcutorture kernel module that can
8 be loaded to run a torture test. The test periodically outputs
9 status messages via printk(), which can be examined via the dmesg
10 command (perhaps grepping for "torture"). The test is started
11 when the module is loaded, and stops when the module is unloaded.
13 CONFIG_RCU_TORTURE_TEST_RUNNABLE
15 It is also possible to specify CONFIG_RCU_TORTURE_TEST=y, which will
16 result in the tests being loaded into the base kernel. In this case,
17 the CONFIG_RCU_TORTURE_TEST_RUNNABLE config option is used to specify
18 whether the RCU torture tests are to be started immediately during
19 boot or whether the /proc/sys/kernel/rcutorture_runnable file is used
20 to enable them. This /proc file can be used to repeatedly pause and
21 restart the tests, regardless of the initial state specified by the
22 CONFIG_RCU_TORTURE_TEST_RUNNABLE config option.
24 You 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
26 this can sometimes be useful in finding boot-time bugs.
31 This module has the following parameters:
33 fqs_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.
39 fqs_holdoff Holdoff time (in microseconds) between consecutive calls
40 to force_quiescent_state() within a burst.
42 fqs_stutter Wait time (in seconds) between consecutive bursts
43 of calls to force_quiescent_state().
45 irqreader Says to invoke RCU readers from irq level. This is currently
46 done via timers. Defaults to "1" for variants of RCU that
47 permit this. (Or, more accurately, variants of RCU that do
48 -not- permit this know to ignore this variable.)
50 nfakewriters This is the number of RCU fake writer threads to run. Fake
51 writer threads repeatedly use the synchronous "wait for
52 current readers" function of the interface selected by
53 torture_type, with a delay between calls to allow for various
54 different numbers of writers running in parallel.
55 nfakewriters defaults to 4, which provides enough parallelism
56 to trigger special cases caused by multiple writers, such as
57 the synchronize_srcu() early return optimization.
59 nreaders This is the number of RCU reading threads supported.
60 The default is twice the number of CPUs. Why twice?
61 To properly exercise RCU implementations with preemptible
62 read-side critical sections.
65 The number of seconds to keep the test threads affinitied
66 to a particular subset of the CPUs, defaults to 3 seconds.
67 Used in conjunction with test_no_idle_hz.
69 stat_interval The number of seconds between output of torture
70 statistics (via printk()). Regardless of the interval,
71 statistics are printed when the module is unloaded.
72 Setting the interval to zero causes the statistics to
73 be printed -only- when the module is unloaded, and this
76 stutter The length of time to run the test before pausing for this
77 same period of time. Defaults to "stutter=5", so as
78 to run and pause for (roughly) five-second intervals.
79 Specifying "stutter=0" causes the test to run continuously
80 without pausing, which is the old default behavior.
82 test_boost Whether or not to test the ability of RCU to do priority
83 boosting. Defaults to "test_boost=1", which performs
84 RCU priority-inversion testing only if the selected
85 RCU implementation supports priority boosting. Specifying
86 "test_boost=0" never performs RCU priority-inversion
87 testing. Specifying "test_boost=2" performs RCU
88 priority-inversion testing even if the selected RCU
89 implementation does not support RCU priority boosting,
90 which can be used to test rcutorture's ability to
91 carry out RCU priority-inversion testing.
94 The number of seconds in an RCU priority-inversion test
95 cycle. Defaults to "test_boost_interval=7". It is
96 usually wise for this value to be relatively prime to
97 the value selected for "stutter".
100 The number of seconds to do RCU priority-inversion testing
101 within any given "test_boost_interval". Defaults to
102 "test_boost_duration=4".
104 test_no_idle_hz Whether or not to test the ability of RCU to operate in
105 a kernel that disables the scheduling-clock interrupt to
106 idle CPUs. Boolean parameter, "1" to test, "0" otherwise.
107 Defaults to omitting this test.
109 torture_type The type of RCU to test, with string values as follows:
111 "rcu": rcu_read_lock(), rcu_read_unlock() and call_rcu().
113 "rcu_sync": rcu_read_lock(), rcu_read_unlock(), and
116 "rcu_expedited": rcu_read_lock(), rcu_read_unlock(), and
117 synchronize_rcu_expedited().
119 "rcu_bh": rcu_read_lock_bh(), rcu_read_unlock_bh(), and
122 "rcu_bh_sync": rcu_read_lock_bh(), rcu_read_unlock_bh(),
123 and synchronize_rcu_bh().
125 "rcu_bh_expedited": rcu_read_lock_bh(), rcu_read_unlock_bh(),
126 and synchronize_rcu_bh_expedited().
128 "srcu": srcu_read_lock(), srcu_read_unlock() and
131 "srcu_expedited": srcu_read_lock(), srcu_read_unlock() and
132 synchronize_srcu_expedited().
134 "sched": preempt_disable(), preempt_enable(), and
137 "sched_sync": preempt_disable(), preempt_enable(), and
140 "sched_expedited": preempt_disable(), preempt_enable(), and
141 synchronize_sched_expedited().
145 verbose Enable debug printk()s. Default is disabled.
150 The statistics output is as follows:
152 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
153 rcu-torture: rtc: (null) ver: 155441 tfle: 0 rta: 155441 rtaf: 8884 rtf: 155440 rtmbe: 0 rtbke: 0 rtbre: 0 rtbf: 0 rtb: 0 nt: 3055767
154 rcu-torture: Reader Pipe: 727860534 34213 0 0 0 0 0 0 0 0 0
155 rcu-torture: Reader Batch: 727877838 17003 0 0 0 0 0 0 0 0 0
156 rcu-torture: Free-Block Circulation: 155440 155440 155440 155440 155440 155440 155440 155440 155440 155440 0
157 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
159 The command "dmesg | grep torture:" will extract this information on
160 most systems. On more esoteric configurations, it may be necessary to
161 use other commands to access the output of the printk()s used by
162 the RCU torture test. The printk()s use KERN_ALERT, so they should
165 The first and last lines show the rcutorture module parameters, and the
166 last line shows either "SUCCESS" or "FAILURE", based on rcutorture's
167 automatic determination as to whether RCU operated correctly.
169 The entries are as follows:
171 o "rtc": The hexadecimal address of the structure currently visible
174 o "ver": The number of times since boot that the RCU writer task
175 has changed the structure visible to readers.
177 o "tfle": If non-zero, indicates that the "torture freelist"
178 containing structures to be placed into the "rtc" area is empty.
179 This condition is important, since it can fool you into thinking
180 that RCU is working when it is not. :-/
182 o "rta": Number of structures allocated from the torture freelist.
184 o "rtaf": Number of allocations from the torture freelist that have
185 failed due to the list being empty. It is not unusual for this
186 to be non-zero, but it is bad for it to be a large fraction of
187 the value indicated by "rta".
189 o "rtf": Number of frees into the torture freelist.
191 o "rtmbe": A non-zero value indicates that rcutorture believes that
192 rcu_assign_pointer() and rcu_dereference() are not working
193 correctly. This value should be zero.
195 o "rtbke": rcutorture was unable to create the real-time kthreads
196 used to force RCU priority inversion. This value should be zero.
198 o "rtbre": Although rcutorture successfully created the kthreads
199 used to force RCU priority inversion, it was unable to set them
200 to the real-time priority level of 1. This value should be zero.
202 o "rtbf": The number of times that RCU priority boosting failed
203 to resolve RCU priority inversion.
205 o "rtb": The number of times that rcutorture attempted to force
206 an RCU priority inversion condition. If you are testing RCU
207 priority boosting via the "test_boost" module parameter, this
208 value should be non-zero.
210 o "nt": The number of times rcutorture ran RCU read-side code from
211 within a timer handler. This value should be non-zero only
212 if you specified the "irqreader" module parameter.
214 o "Reader Pipe": Histogram of "ages" of structures seen by readers.
215 If any entries past the first two are non-zero, RCU is broken.
216 And rcutorture prints the error flag string "!!!" to make sure
217 you notice. The age of a newly allocated structure is zero,
218 it becomes one when removed from reader visibility, and is
219 incremented once per grace period subsequently -- and is freed
220 after passing through (RCU_TORTURE_PIPE_LEN-2) grace periods.
222 The output displayed above was taken from a correctly working
223 RCU. If you want to see what it looks like when broken, break
226 o "Reader Batch": Another histogram of "ages" of structures seen
227 by readers, but in terms of counter flips (or batches) rather
228 than in terms of grace periods. The legal number of non-zero
229 entries is again two. The reason for this separate view is that
230 it is sometimes easier to get the third entry to show up in the
231 "Reader Batch" list than in the "Reader Pipe" list.
233 o "Free-Block Circulation": Shows the number of torture structures
234 that have reached a given point in the pipeline. The first element
235 should closely correspond to the number of structures allocated,
236 the second to the number that have been removed from reader view,
237 and all but the last remaining to the corresponding number of
238 passes through a grace period. The last entry should be zero,
239 as it is only incremented if a torture structure's counter
240 somehow gets incremented farther than it should.
242 Different implementations of RCU can provide implementation-specific
243 additional information. For example, SRCU provides the following
246 srcu-torture: per-CPU(idx=1): 0(0,1) 1(0,1) 2(0,0) 3(0,1)
248 This line shows the per-CPU counter state. The numbers in parentheses are
249 the values of the "old" and "current" counters for the corresponding CPU.
250 The "idx" value maps the "old" and "current" values to the underlying
251 array, and is useful for debugging.
256 The following script may be used to torture RCU:
263 dmesg | grep torture:
265 The output can be manually inspected for the error flag of "!!!".
266 One could of course create a more elaborate script that automatically
267 checked for such errors. The "rmmod" command forces a "SUCCESS" or
268 "FAILURE" indication to be printk()ed.