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 irqreaders Says to invoke RCU readers from irq level. This is currently
34 done via timers. Defaults to "1" for variants of RCU that
35 permit this. (Or, more accurately, variants of RCU that do
36 -not- permit this know to ignore this variable.)
38 nfakewriters This is the number of RCU fake writer threads to run. Fake
39 writer threads repeatedly use the synchronous "wait for
40 current readers" function of the interface selected by
41 torture_type, with a delay between calls to allow for various
42 different numbers of writers running in parallel.
43 nfakewriters defaults to 4, which provides enough parallelism
44 to trigger special cases caused by multiple writers, such as
45 the synchronize_srcu() early return optimization.
47 nreaders This is the number of RCU reading threads supported.
48 The default is twice the number of CPUs. Why twice?
49 To properly exercise RCU implementations with preemptible
50 read-side critical sections.
53 The number of seconds to keep the test threads affinitied
54 to a particular subset of the CPUs, defaults to 3 seconds.
55 Used in conjunction with test_no_idle_hz.
57 stat_interval The number of seconds between output of torture
58 statistics (via printk()). Regardless of the interval,
59 statistics are printed when the module is unloaded.
60 Setting the interval to zero causes the statistics to
61 be printed -only- when the module is unloaded, and this
64 stutter The length of time to run the test before pausing for this
65 same period of time. Defaults to "stutter=5", so as
66 to run and pause for (roughly) five-second intervals.
67 Specifying "stutter=0" causes the test to run continuously
68 without pausing, which is the old default behavior.
70 test_no_idle_hz Whether or not to test the ability of RCU to operate in
71 a kernel that disables the scheduling-clock interrupt to
72 idle CPUs. Boolean parameter, "1" to test, "0" otherwise.
73 Defaults to omitting this test.
75 torture_type The type of RCU to test: "rcu" for the rcu_read_lock() API,
76 "rcu_sync" for rcu_read_lock() with synchronous reclamation,
77 "rcu_bh" for the rcu_read_lock_bh() API, "rcu_bh_sync" for
78 rcu_read_lock_bh() with synchronous reclamation, "srcu" for
79 the "srcu_read_lock()" API, "sched" for the use of
80 preempt_disable() together with synchronize_sched(),
81 and "sched_expedited" for the use of preempt_disable()
82 with synchronize_sched_expedited().
84 verbose Enable debug printk()s. Default is disabled.
89 The statistics output is as follows:
91 rcu-torture: --- Start of test: nreaders=16 stat_interval=0 verbose=0
92 rcu-torture: rtc: 0000000000000000 ver: 1916 tfle: 0 rta: 1916 rtaf: 0 rtf: 1915
93 rcu-torture: Reader Pipe: 1466408 9747 0 0 0 0 0 0 0 0 0
94 rcu-torture: Reader Batch: 1464477 11678 0 0 0 0 0 0 0 0
95 rcu-torture: Free-Block Circulation: 1915 1915 1915 1915 1915 1915 1915 1915 1915 1915 0
96 rcu-torture: --- End of test
98 The command "dmesg | grep torture:" will extract this information on
99 most systems. On more esoteric configurations, it may be necessary to
100 use other commands to access the output of the printk()s used by
101 the RCU torture test. The printk()s use KERN_ALERT, so they should
104 The entries are as follows:
106 o "rtc": The hexadecimal address of the structure currently visible
109 o "ver": The number of times since boot that the rcutw writer task
110 has changed the structure visible to readers.
112 o "tfle": If non-zero, indicates that the "torture freelist"
113 containing structure to be placed into the "rtc" area is empty.
114 This condition is important, since it can fool you into thinking
115 that RCU is working when it is not. :-/
117 o "rta": Number of structures allocated from the torture freelist.
119 o "rtaf": Number of allocations from the torture freelist that have
120 failed due to the list being empty.
122 o "rtf": Number of frees into the torture freelist.
124 o "Reader Pipe": Histogram of "ages" of structures seen by readers.
125 If any entries past the first two are non-zero, RCU is broken.
126 And rcutorture prints the error flag string "!!!" to make sure
127 you notice. The age of a newly allocated structure is zero,
128 it becomes one when removed from reader visibility, and is
129 incremented once per grace period subsequently -- and is freed
130 after passing through (RCU_TORTURE_PIPE_LEN-2) grace periods.
132 The output displayed above was taken from a correctly working
133 RCU. If you want to see what it looks like when broken, break
136 o "Reader Batch": Another histogram of "ages" of structures seen
137 by readers, but in terms of counter flips (or batches) rather
138 than in terms of grace periods. The legal number of non-zero
139 entries is again two. The reason for this separate view is that
140 it is sometimes easier to get the third entry to show up in the
141 "Reader Batch" list than in the "Reader Pipe" list.
143 o "Free-Block Circulation": Shows the number of torture structures
144 that have reached a given point in the pipeline. The first element
145 should closely correspond to the number of structures allocated,
146 the second to the number that have been removed from reader view,
147 and all but the last remaining to the corresponding number of
148 passes through a grace period. The last entry should be zero,
149 as it is only incremented if a torture structure's counter
150 somehow gets incremented farther than it should.
152 Different implementations of RCU can provide implementation-specific
153 additional information. For example, SRCU provides the following:
155 srcu-torture: rtc: f8cf46a8 ver: 355 tfle: 0 rta: 356 rtaf: 0 rtf: 346 rtmbe: 0
156 srcu-torture: Reader Pipe: 559738 939 0 0 0 0 0 0 0 0 0
157 srcu-torture: Reader Batch: 560434 243 0 0 0 0 0 0 0 0
158 srcu-torture: Free-Block Circulation: 355 354 353 352 351 350 349 348 347 346 0
159 srcu-torture: per-CPU(idx=1): 0(0,1) 1(0,1) 2(0,0) 3(0,1)
161 The first four lines are similar to those for RCU. The last line shows
162 the per-CPU counter state. The numbers in parentheses are the values
163 of the "old" and "current" counters for the corresponding CPU. The
164 "idx" value maps the "old" and "current" values to the underlying array,
165 and is useful for debugging.
167 Similarly, sched_expedited RCU provides the following:
169 sched_expedited-torture: rtc: d0000000016c1880 ver: 1090796 tfle: 0 rta: 1090796 rtaf: 0 rtf: 1090787 rtmbe: 0 nt: 27713319
170 sched_expedited-torture: Reader Pipe: 12660320201 95875 0 0 0 0 0 0 0 0 0
171 sched_expedited-torture: Reader Batch: 12660424885 0 0 0 0 0 0 0 0 0 0
172 sched_expedited-torture: Free-Block Circulation: 1090795 1090795 1090794 1090793 1090792 1090791 1090790 1090789 1090788 1090787 0
173 state: -1 / 0:0 3:0 4:0
175 As before, the first four lines are similar to those for RCU.
176 The last line shows the task-migration state. The first number is
177 -1 if synchronize_sched_expedited() is idle, -2 if in the process of
178 posting wakeups to the migration kthreads, and N when waiting on CPU N.
179 Each of the colon-separated fields following the "/" is a CPU:state pair.
180 Valid states are "0" for idle, "1" for waiting for quiescent state,
181 "2" for passed through quiescent state, and "3" when a race with a
182 CPU-hotplug event forces use of the synchronize_sched() primitive.
187 The following script may be used to torture RCU:
194 dmesg | grep torture:
196 The output can be manually inspected for the error flag of "!!!".
197 One could of course create a more elaborate script that automatically
198 checked for such errors. The "rmmod" command forces a "SUCCESS" or
199 "FAILURE" indication to be printk()ed.