xref: /openbmc/linux/Documentation/RCU/torture.rst (revision 842ed298)
1.. SPDX-License-Identifier: GPL-2.0
2
3==========================
4RCU Torture Test Operation
5==========================
6
7
8CONFIG_RCU_TORTURE_TEST
9=======================
10
11The CONFIG_RCU_TORTURE_TEST config option is available for all RCU
12implementations.  It creates an rcutorture kernel module that can
13be loaded to run a torture test.  The test periodically outputs
14status messages via printk(), which can be examined via the dmesg
15command (perhaps grepping for "torture").  The test is started
16when the module is loaded, and stops when the module is unloaded.
17
18Module parameters are prefixed by "rcutorture." in
19Documentation/admin-guide/kernel-parameters.txt.
20
21Output
22======
23
24The statistics output is as follows::
25
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
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
28	rcu-torture: Reader Pipe:  727860534 34213 0 0 0 0 0 0 0 0 0
29	rcu-torture: Reader Batch:  727877838 17003 0 0 0 0 0 0 0 0 0
30	rcu-torture: Free-Block Circulation:  155440 155440 155440 155440 155440 155440 155440 155440 155440 155440 0
31	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
32
33The command "dmesg | grep torture:" will extract this information on
34most systems.  On more esoteric configurations, it may be necessary to
35use other commands to access the output of the printk()s used by
36the RCU torture test.  The printk()s use KERN_ALERT, so they should
37be evident.  ;-)
38
39The first and last lines show the rcutorture module parameters, and the
40last line shows either "SUCCESS" or "FAILURE", based on rcutorture's
41automatic determination as to whether RCU operated correctly.
42
43The entries are as follows:
44
45*	"rtc": The hexadecimal address of the structure currently visible
46	to readers.
47
48*	"ver": The number of times since boot that the RCU writer task
49	has changed the structure visible to readers.
50
51*	"tfle": If non-zero, indicates that the "torture freelist"
52	containing structures to be placed into the "rtc" area is empty.
53	This condition is important, since it can fool you into thinking
54	that RCU is working when it is not.  :-/
55
56*	"rta": Number of structures allocated from the torture freelist.
57
58*	"rtaf": Number of allocations from the torture freelist that have
59	failed due to the list being empty.  It is not unusual for this
60	to be non-zero, but it is bad for it to be a large fraction of
61	the value indicated by "rta".
62
63*	"rtf": Number of frees into the torture freelist.
64
65*	"rtmbe": A non-zero value indicates that rcutorture believes that
66	rcu_assign_pointer() and rcu_dereference() are not working
67	correctly.  This value should be zero.
68
69*	"rtbe": A non-zero value indicates that one of the rcu_barrier()
70	family of functions is not working correctly.
71
72*	"rtbke": rcutorture was unable to create the real-time kthreads
73	used to force RCU priority inversion.  This value should be zero.
74
75*	"rtbre": Although rcutorture successfully created the kthreads
76	used to force RCU priority inversion, it was unable to set them
77	to the real-time priority level of 1.  This value should be zero.
78
79*	"rtbf": The number of times that RCU priority boosting failed
80	to resolve RCU priority inversion.
81
82*	"rtb": The number of times that rcutorture attempted to force
83	an RCU priority inversion condition.  If you are testing RCU
84	priority boosting via the "test_boost" module parameter, this
85	value should be non-zero.
86
87*	"nt": The number of times rcutorture ran RCU read-side code from
88	within a timer handler.  This value should be non-zero only
89	if you specified the "irqreader" module parameter.
90
91*	"Reader Pipe": Histogram of "ages" of structures seen by readers.
92	If any entries past the first two are non-zero, RCU is broken.
93	And rcutorture prints the error flag string "!!!" to make sure
94	you notice.  The age of a newly allocated structure is zero,
95	it becomes one when removed from reader visibility, and is
96	incremented once per grace period subsequently -- and is freed
97	after passing through (RCU_TORTURE_PIPE_LEN-2) grace periods.
98
99	The output displayed above was taken from a correctly working
100	RCU.  If you want to see what it looks like when broken, break
101	it yourself.  ;-)
102
103*	"Reader Batch": Another histogram of "ages" of structures seen
104	by readers, but in terms of counter flips (or batches) rather
105	than in terms of grace periods.  The legal number of non-zero
106	entries is again two.  The reason for this separate view is that
107	it is sometimes easier to get the third entry to show up in the
108	"Reader Batch" list than in the "Reader Pipe" list.
109
110*	"Free-Block Circulation": Shows the number of torture structures
111	that have reached a given point in the pipeline.  The first element
112	should closely correspond to the number of structures allocated,
113	the second to the number that have been removed from reader view,
114	and all but the last remaining to the corresponding number of
115	passes through a grace period.  The last entry should be zero,
116	as it is only incremented if a torture structure's counter
117	somehow gets incremented farther than it should.
118
119Different implementations of RCU can provide implementation-specific
120additional information.  For example, Tree SRCU provides the following
121additional line::
122
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)
124
125This line shows the per-CPU counter state, in this case for Tree SRCU
126using a dynamically allocated srcu_struct (hence "srcud-" rather than
127"srcu-").  The numbers in parentheses are the values of the "old" and
128"current" counters for the corresponding CPU.  The "idx" value maps the
129"old" and "current" values to the underlying array, and is useful for
130debugging.  The final "T" entry contains the totals of the counters.
131
132Usage on Specific Kernel Builds
133===============================
134
135It is sometimes desirable to torture RCU on a specific kernel build,
136for example, when preparing to put that kernel build into production.
137In that case, the kernel should be built with CONFIG_RCU_TORTURE_TEST=m
138so that the test can be started using modprobe and terminated using rmmod.
139
140For example, the following script may be used to torture RCU::
141
142	#!/bin/sh
143
144	modprobe rcutorture
145	sleep 3600
146	rmmod rcutorture
147	dmesg | grep torture:
148
149The output can be manually inspected for the error flag of "!!!".
150One could of course create a more elaborate script that automatically
151checked for such errors.  The "rmmod" command forces a "SUCCESS",
152"FAILURE", or "RCU_HOTPLUG" indication to be printk()ed.  The first
153two are self-explanatory, while the last indicates that while there
154were no RCU failures, CPU-hotplug problems were detected.
155
156
157Usage on Mainline Kernels
158=========================
159
160When using rcutorture to test changes to RCU itself, it is often
161necessary to build a number of kernels in order to test that change
162across a broad range of combinations of the relevant Kconfig options
163and of the relevant kernel boot parameters.  In this situation, use
164of modprobe and rmmod can be quite time-consuming and error-prone.
165
166Therefore, the tools/testing/selftests/rcutorture/bin/kvm.sh
167script is available for mainline testing for x86, arm64, and
168powerpc.  By default, it will run the series of tests specified by
169tools/testing/selftests/rcutorture/configs/rcu/CFLIST, with each test
170running for 30 minutes within a guest OS using a minimal userspace
171supplied by an automatically generated initrd.  After the tests are
172complete, the resulting build products and console output are analyzed
173for errors and the results of the runs are summarized.
174
175On larger systems, rcutorture testing can be accelerated by passing the
176--cpus argument to kvm.sh.  For example, on a 64-CPU system, "--cpus 43"
177would use up to 43 CPUs to run tests concurrently, which as of v5.4 would
178complete all the scenarios in two batches, reducing the time to complete
179from about eight hours to about one hour (not counting the time to build
180the sixteen kernels).  The "--dryrun sched" argument will not run tests,
181but rather tell you how the tests would be scheduled into batches.  This
182can be useful when working out how many CPUs to specify in the --cpus
183argument.
184
185Not all changes require that all scenarios be run.  For example, a change
186to Tree SRCU might run only the SRCU-N and SRCU-P scenarios using the
187--configs argument to kvm.sh as follows:  "--configs 'SRCU-N SRCU-P'".
188Large systems can run multiple copies of of the full set of scenarios,
189for example, a system with 448 hardware threads can run five instances
190of the full set concurrently.  To make this happen::
191
192	kvm.sh --cpus 448 --configs '5*CFLIST'
193
194Alternatively, such a system can run 56 concurrent instances of a single
195eight-CPU scenario::
196
197	kvm.sh --cpus 448 --configs '56*TREE04'
198
199Or 28 concurrent instances of each of two eight-CPU scenarios::
200
201	kvm.sh --cpus 448 --configs '28*TREE03 28*TREE04'
202
203Of course, each concurrent instance will use memory, which can be
204limited using the --memory argument, which defaults to 512M.  Small
205values for memory may require disabling the callback-flooding tests
206using the --bootargs parameter discussed below.
207
208Sometimes additional debugging is useful, and in such cases the --kconfig
209parameter to kvm.sh may be used, for example, ``--kconfig 'CONFIG_KASAN=y'``.
210
211Kernel boot arguments can also be supplied, for example, to control
212rcutorture's module parameters.  For example, to test a change to RCU's
213CPU stall-warning code, use "--bootargs 'rcutorture.stall_cpu=30'".
214This will of course result in the scripting reporting a failure, namely
215the resuling RCU CPU stall warning.  As noted above, reducing memory may
216require disabling rcutorture's callback-flooding tests::
217
218	kvm.sh --cpus 448 --configs '56*TREE04' --memory 128M \
219		--bootargs 'rcutorture.fwd_progress=0'
220
221Sometimes all that is needed is a full set of kernel builds.  This is
222what the --buildonly argument does.
223
224Finally, the --trust-make argument allows each kernel build to reuse what
225it can from the previous kernel build.
226
227There are additional more arcane arguments that are documented in the
228source code of the kvm.sh script.
229
230If a run contains failures, the number of buildtime and runtime failures
231is listed at the end of the kvm.sh output, which you really should redirect
232to a file.  The build products and console output of each run is kept in
233tools/testing/selftests/rcutorture/res in timestamped directories.  A
234given directory can be supplied to kvm-find-errors.sh in order to have
235it cycle you through summaries of errors and full error logs.  For example::
236
237	tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh \
238		tools/testing/selftests/rcutorture/res/2020.01.20-15.54.23
239
240However, it is often more convenient to access the files directly.
241Files pertaining to all scenarios in a run reside in the top-level
242directory (2020.01.20-15.54.23 in the example above), while per-scenario
243files reside in a subdirectory named after the scenario (for example,
244"TREE04").  If a given scenario ran more than once (as in "--configs
245'56*TREE04'" above), the directories corresponding to the second and
246subsequent runs of that scenario include a sequence number, for example,
247"TREE04.2", "TREE04.3", and so on.
248
249The most frequently used file in the top-level directory is testid.txt.
250If the test ran in a git repository, then this file contains the commit
251that was tested and any uncommitted changes in diff format.
252
253The most frequently used files in each per-scenario-run directory are:
254
255.config:
256	This file contains the Kconfig options.
257
258Make.out:
259	This contains build output for a specific scenario.
260
261console.log:
262	This contains the console output for a specific scenario.
263	This file may be examined once the kernel has booted, but
264	it might not exist if the build failed.
265
266vmlinux:
267	This contains the kernel, which can be useful with tools like
268	objdump and gdb.
269
270A number of additional files are available, but are less frequently used.
271Many are intended for debugging of rcutorture itself or of its scripting.
272
273As of v5.4, a successful run with the default set of scenarios produces
274the 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
294