summaryrefslogtreecommitdiffstats
path: root/tools/testing/selftests/cgroup/test_cpu.c
blob: 186bf96f6a284651b9953d75a1f91806db118821 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
// SPDX-License-Identifier: GPL-2.0

#define _GNU_SOURCE
#include <linux/limits.h>
#include <sys/sysinfo.h>
#include <sys/wait.h>
#include <errno.h>
#include <pthread.h>
#include <stdio.h>
#include <time.h>

#include "../kselftest.h"
#include "cgroup_util.h"

enum hog_clock_type {
	// Count elapsed time using the CLOCK_PROCESS_CPUTIME_ID clock.
	CPU_HOG_CLOCK_PROCESS,
	// Count elapsed time using system wallclock time.
	CPU_HOG_CLOCK_WALL,
};

struct cpu_hogger {
	char *cgroup;
	pid_t pid;
	long usage;
};

struct cpu_hog_func_param {
	int nprocs;
	struct timespec ts;
	enum hog_clock_type clock_type;
};

/*
 * This test creates two nested cgroups with and without enabling
 * the cpu controller.
 */
static int test_cpucg_subtree_control(const char *root)
{
	char *parent = NULL, *child = NULL, *parent2 = NULL, *child2 = NULL;
	int ret = KSFT_FAIL;

	// Create two nested cgroups with the cpu controller enabled.
	parent = cg_name(root, "cpucg_test_0");
	if (!parent)
		goto cleanup;

	if (cg_create(parent))
		goto cleanup;

	if (cg_write(parent, "cgroup.subtree_control", "+cpu"))
		goto cleanup;

	child = cg_name(parent, "cpucg_test_child");
	if (!child)
		goto cleanup;

	if (cg_create(child))
		goto cleanup;

	if (cg_read_strstr(child, "cgroup.controllers", "cpu"))
		goto cleanup;

	// Create two nested cgroups without enabling the cpu controller.
	parent2 = cg_name(root, "cpucg_test_1");
	if (!parent2)
		goto cleanup;

	if (cg_create(parent2))
		goto cleanup;

	child2 = cg_name(parent2, "cpucg_test_child");
	if (!child2)
		goto cleanup;

	if (cg_create(child2))
		goto cleanup;

	if (!cg_read_strstr(child2, "cgroup.controllers", "cpu"))
		goto cleanup;

	ret = KSFT_PASS;

cleanup:
	cg_destroy(child);
	free(child);
	cg_destroy(child2);
	free(child2);
	cg_destroy(parent);
	free(parent);
	cg_destroy(parent2);
	free(parent2);

	return ret;
}

static void *hog_cpu_thread_func(void *arg)
{
	while (1)
		;

	return NULL;
}

static struct timespec
timespec_sub(const struct timespec *lhs, const struct timespec *rhs)
{
	struct timespec zero = {
		.tv_sec = 0,
		.tv_nsec = 0,
	};
	struct timespec ret;

	if (lhs->tv_sec < rhs->tv_sec)
		return zero;

	ret.tv_sec = lhs->tv_sec - rhs->tv_sec;

	if (lhs->tv_nsec < rhs->tv_nsec) {
		if (ret.tv_sec == 0)
			return zero;

		ret.tv_sec--;
		ret.tv_nsec = NSEC_PER_SEC - rhs->tv_nsec + lhs->tv_nsec;
	} else
		ret.tv_nsec = lhs->tv_nsec - rhs->tv_nsec;

	return ret;
}

static int hog_cpus_timed(const char *cgroup, void *arg)
{
	const struct cpu_hog_func_param *param =
		(struct cpu_hog_func_param *)arg;
	struct timespec ts_run = param->ts;
	struct timespec ts_remaining = ts_run;
	struct timespec ts_start;
	int i, ret;

	ret = clock_gettime(CLOCK_MONOTONIC, &ts_start);
	if (ret != 0)
		return ret;

	for (i = 0; i < param->nprocs; i++) {
		pthread_t tid;

		ret = pthread_create(&tid, NULL, &hog_cpu_thread_func, NULL);
		if (ret != 0)
			return ret;
	}

	while (ts_remaining.tv_sec > 0 || ts_remaining.tv_nsec > 0) {
		struct timespec ts_total;

		ret = nanosleep(&ts_remaining, NULL);
		if (ret && errno != EINTR)
			return ret;

		if (param->clock_type == CPU_HOG_CLOCK_PROCESS) {
			ret = clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &ts_total);
			if (ret != 0)
				return ret;
		} else {
			struct timespec ts_current;

			ret = clock_gettime(CLOCK_MONOTONIC, &ts_current);
			if (ret != 0)
				return ret;

			ts_total = timespec_sub(&ts_current, &ts_start);
		}

		ts_remaining = timespec_sub(&ts_run, &ts_total);
	}

	return 0;
}

/*
 * Creates a cpu cgroup, burns a CPU for a few quanta, and verifies that
 * cpu.stat shows the expected output.
 */
static int test_cpucg_stats(const char *root)
{
	int ret = KSFT_FAIL;
	long usage_usec, user_usec, system_usec;
	long usage_seconds = 2;
	long expected_usage_usec = usage_seconds * USEC_PER_SEC;
	char *cpucg;

	cpucg = cg_name(root, "cpucg_test");
	if (!cpucg)
		goto cleanup;

	if (cg_create(cpucg))
		goto cleanup;

	usage_usec = cg_read_key_long(cpucg, "cpu.stat", "usage_usec");
	user_usec = cg_read_key_long(cpucg, "cpu.stat", "user_usec");
	system_usec = cg_read_key_long(cpucg, "cpu.stat", "system_usec");
	if (usage_usec != 0 || user_usec != 0 || system_usec != 0)
		goto cleanup;

	struct cpu_hog_func_param param = {
		.nprocs = 1,
		.ts = {
			.tv_sec = usage_seconds,
			.tv_nsec = 0,
		},
		.clock_type = CPU_HOG_CLOCK_PROCESS,
	};
	if (cg_run(cpucg, hog_cpus_timed, (void *)&param))
		goto cleanup;

	usage_usec = cg_read_key_long(cpucg, "cpu.stat", "usage_usec");
	user_usec = cg_read_key_long(cpucg, "cpu.stat", "user_usec");
	if (user_usec <= 0)
		goto cleanup;

	if (!values_close(usage_usec, expected_usage_usec, 1))
		goto cleanup;

	ret = KSFT_PASS;

cleanup:
	cg_destroy(cpucg);
	free(cpucg);

	return ret;
}

static int
run_cpucg_weight_test(
		const char *root,
		pid_t (*spawn_child)(const struct cpu_hogger *child),
		int (*validate)(const struct cpu_hogger *children, int num_children))
{
	int ret = KSFT_FAIL, i;
	char *parent = NULL;
	struct cpu_hogger children[3] = {NULL};

	parent = cg_name(root, "cpucg_test_0");
	if (!parent)
		goto cleanup;

	if (cg_create(parent))
		goto cleanup;

	if (cg_write(parent, "cgroup.subtree_control", "+cpu"))
		goto cleanup;

	for (i = 0; i < ARRAY_SIZE(children); i++) {
		children[i].cgroup = cg_name_indexed(parent, "cpucg_child", i);
		if (!children[i].cgroup)
			goto cleanup;

		if (cg_create(children[i].cgroup))
			goto cleanup;

		if (cg_write_numeric(children[i].cgroup, "cpu.weight",
					50 * (i + 1)))
			goto cleanup;
	}

	for (i = 0; i < ARRAY_SIZE(children); i++) {
		pid_t pid = spawn_child(&children[i]);
		if (pid <= 0)
			goto cleanup;
		children[i].pid = pid;
	}

	for (i = 0; i < ARRAY_SIZE(children); i++) {
		int retcode;

		waitpid(children[i].pid, &retcode, 0);
		if (!WIFEXITED(retcode))
			goto cleanup;
		if (WEXITSTATUS(retcode))
			goto cleanup;
	}

	for (i = 0; i < ARRAY_SIZE(children); i++)
		children[i].usage = cg_read_key_long(children[i].cgroup,
				"cpu.stat", "usage_usec");

	if (validate(children, ARRAY_SIZE(children)))
		goto cleanup;

	ret = KSFT_PASS;
cleanup:
	for (i = 0; i < ARRAY_SIZE(children); i++) {
		cg_destroy(children[i].cgroup);
		free(children[i].cgroup);
	}
	cg_destroy(parent);
	free(parent);

	return ret;
}

static pid_t weight_hog_ncpus(const struct cpu_hogger *child, int ncpus)
{
	long usage_seconds = 10;
	struct cpu_hog_func_param param = {
		.nprocs = ncpus,
		.ts = {
			.tv_sec = usage_seconds,
			.tv_nsec = 0,
		},
		.clock_type = CPU_HOG_CLOCK_WALL,
	};
	return cg_run_nowait(child->cgroup, hog_cpus_timed, (void *)&param);
}

static pid_t weight_hog_all_cpus(const struct cpu_hogger *child)
{
	return weight_hog_ncpus(child, get_nprocs());
}

static int
overprovision_validate(const struct cpu_hogger *children, int num_children)
{
	int ret = KSFT_FAIL, i;

	for (i = 0; i < num_children - 1; i++) {
		long delta;

		if (children[i + 1].usage <= children[i].usage)
			goto cleanup;

		delta = children[i + 1].usage - children[i].usage;
		if (!values_close(delta, children[0].usage, 35))
			goto cleanup;
	}

	ret = KSFT_PASS;
cleanup:
	return ret;
}

/*
 * First, this test creates the following hierarchy:
 * A
 * A/B     cpu.weight = 50
 * A/C     cpu.weight = 100
 * A/D     cpu.weight = 150
 *
 * A separate process is then created for each child cgroup which spawns as
 * many threads as there are cores, and hogs each CPU as much as possible
 * for some time interval.
 *
 * Once all of the children have exited, we verify that each child cgroup
 * was given proportional runtime as informed by their cpu.weight.
 */
static int test_cpucg_weight_overprovisioned(const char *root)
{
	return run_cpucg_weight_test(root, weight_hog_all_cpus,
			overprovision_validate);
}

static pid_t weight_hog_one_cpu(const struct cpu_hogger *child)
{
	return weight_hog_ncpus(child, 1);
}

static int
underprovision_validate(const struct cpu_hogger *children, int num_children)
{
	int ret = KSFT_FAIL, i;

	for (i = 0; i < num_children - 1; i++) {
		if (!values_close(children[i + 1].usage, children[0].usage, 15))
			goto cleanup;
	}

	ret = KSFT_PASS;
cleanup:
	return ret;
}

/*
 * First, this test creates the following hierarchy:
 * A
 * A/B     cpu.weight = 50
 * A/C     cpu.weight = 100
 * A/D     cpu.weight = 150
 *
 * A separate process is then created for each child cgroup which spawns a
 * single thread that hogs a CPU. The testcase is only run on systems that
 * have at least one core per-thread in the child processes.
 *
 * Once all of the children have exited, we verify that each child cgroup
 * had roughly the same runtime despite having different cpu.weight.
 */
static int test_cpucg_weight_underprovisioned(const char *root)
{
	// Only run the test if there are enough cores to avoid overprovisioning
	// the system.
	if (get_nprocs() < 4)
		return KSFT_SKIP;

	return run_cpucg_weight_test(root, weight_hog_one_cpu,
			underprovision_validate);
}

static int
run_cpucg_nested_weight_test(const char *root, bool overprovisioned)
{
	int ret = KSFT_FAIL, i;
	char *parent = NULL, *child = NULL;
	struct cpu_hogger leaf[3] = {NULL};
	long nested_leaf_usage, child_usage;
	int nprocs = get_nprocs();

	if (!overprovisioned) {
		if (nprocs < 4)
			/*
			 * Only run the test if there are enough cores to avoid overprovisioning
			 * the system.
			 */
			return KSFT_SKIP;
		nprocs /= 4;
	}

	parent = cg_name(root, "cpucg_test");
	child = cg_name(parent, "cpucg_child");
	if (!parent || !child)
		goto cleanup;

	if (cg_create(parent))
		goto cleanup;
	if (cg_write(parent, "cgroup.subtree_control", "+cpu"))
		goto cleanup;

	if (cg_create(child))
		goto cleanup;
	if (cg_write(child, "cgroup.subtree_control", "+cpu"))
		goto cleanup;
	if (cg_write(child, "cpu.weight", "1000"))
		goto cleanup;

	for (i = 0; i < ARRAY_SIZE(leaf); i++) {
		const char *ancestor;
		long weight;

		if (i == 0) {
			ancestor = parent;
			weight = 1000;
		} else {
			ancestor = child;
			weight = 5000;
		}
		leaf[i].cgroup = cg_name_indexed(ancestor, "cpucg_leaf", i);
		if (!leaf[i].cgroup)
			goto cleanup;

		if (cg_create(leaf[i].cgroup))
			goto cleanup;

		if (cg_write_numeric(leaf[i].cgroup, "cpu.weight", weight))
			goto cleanup;
	}

	for (i = 0; i < ARRAY_SIZE(leaf); i++) {
		pid_t pid;
		struct cpu_hog_func_param param = {
			.nprocs = nprocs,
			.ts = {
				.tv_sec = 10,
				.tv_nsec = 0,
			},
			.clock_type = CPU_HOG_CLOCK_WALL,
		};

		pid = cg_run_nowait(leaf[i].cgroup, hog_cpus_timed,
				(void *)&param);
		if (pid <= 0)
			goto cleanup;
		leaf[i].pid = pid;
	}

	for (i = 0; i < ARRAY_SIZE(leaf); i++) {
		int retcode;

		waitpid(leaf[i].pid, &retcode, 0);
		if (!WIFEXITED(retcode))
			goto cleanup;
		if (WEXITSTATUS(retcode))
			goto cleanup;
	}

	for (i = 0; i < ARRAY_SIZE(leaf); i++) {
		leaf[i].usage = cg_read_key_long(leaf[i].cgroup,
				"cpu.stat", "usage_usec");
		if (leaf[i].usage <= 0)
			goto cleanup;
	}

	nested_leaf_usage = leaf[1].usage + leaf[2].usage;
	if (overprovisioned) {
		if (!values_close(leaf[0].usage, nested_leaf_usage, 15))
			goto cleanup;
	} else if (!values_close(leaf[0].usage * 2, nested_leaf_usage, 15))
		goto cleanup;


	child_usage = cg_read_key_long(child, "cpu.stat", "usage_usec");
	if (child_usage <= 0)
		goto cleanup;
	if (!values_close(child_usage, nested_leaf_usage, 1))
		goto cleanup;

	ret = KSFT_PASS;
cleanup:
	for (i = 0; i < ARRAY_SIZE(leaf); i++) {
		cg_destroy(leaf[i].cgroup);
		free(leaf[i].cgroup);
	}
	cg_destroy(child);
	free(child);
	cg_destroy(parent);
	free(parent);

	return ret;
}

/*
 * First, this test creates the following hierarchy:
 * A
 * A/B     cpu.weight = 1000
 * A/C     cpu.weight = 1000
 * A/C/D   cpu.weight = 5000
 * A/C/E   cpu.weight = 5000
 *
 * A separate process is then created for each leaf, which spawn nproc threads
 * that burn a CPU for a few seconds.
 *
 * Once all of those processes have exited, we verify that each of the leaf
 * cgroups have roughly the same usage from cpu.stat.
 */
static int
test_cpucg_nested_weight_overprovisioned(const char *root)
{
	return run_cpucg_nested_weight_test(root, true);
}

/*
 * First, this test creates the following hierarchy:
 * A
 * A/B     cpu.weight = 1000
 * A/C     cpu.weight = 1000
 * A/C/D   cpu.weight = 5000
 * A/C/E   cpu.weight = 5000
 *
 * A separate process is then created for each leaf, which nproc / 4 threads
 * that burns a CPU for a few seconds.
 *
 * Once all of those processes have exited, we verify that each of the leaf
 * cgroups have roughly the same usage from cpu.stat.
 */
static int
test_cpucg_nested_weight_underprovisioned(const char *root)
{
	return run_cpucg_nested_weight_test(root, false);
}

/*
 * This test creates a cgroup with some maximum value within a period, and
 * verifies that a process in the cgroup is not overscheduled.
 */
static int test_cpucg_max(const char *root)
{
	int ret = KSFT_FAIL;
	long usage_usec, user_usec;
	long usage_seconds = 1;
	long expected_usage_usec = usage_seconds * USEC_PER_SEC;
	char *cpucg;

	cpucg = cg_name(root, "cpucg_test");
	if (!cpucg)
		goto cleanup;

	if (cg_create(cpucg))
		goto cleanup;

	if (cg_write(cpucg, "cpu.max", "1000"))
		goto cleanup;

	struct cpu_hog_func_param param = {
		.nprocs = 1,
		.ts = {
			.tv_sec = usage_seconds,
			.tv_nsec = 0,
		},
		.clock_type = CPU_HOG_CLOCK_WALL,
	};
	if (cg_run(cpucg, hog_cpus_timed, (void *)&param))
		goto cleanup;

	usage_usec = cg_read_key_long(cpucg, "cpu.stat", "usage_usec");
	user_usec = cg_read_key_long(cpucg, "cpu.stat", "user_usec");
	if (user_usec <= 0)
		goto cleanup;

	if (user_usec >= expected_usage_usec)
		goto cleanup;

	if (values_close(usage_usec, expected_usage_usec, 95))
		goto cleanup;

	ret = KSFT_PASS;

cleanup:
	cg_destroy(cpucg);
	free(cpucg);

	return ret;
}

/*
 * This test verifies that a process inside of a nested cgroup whose parent
 * group has a cpu.max value set, is properly throttled.
 */
static int test_cpucg_max_nested(const char *root)
{
	int ret = KSFT_FAIL;
	long usage_usec, user_usec;
	long usage_seconds = 1;
	long expected_usage_usec = usage_seconds * USEC_PER_SEC;
	char *parent, *child;

	parent = cg_name(root, "cpucg_parent");
	child = cg_name(parent, "cpucg_child");
	if (!parent || !child)
		goto cleanup;

	if (cg_create(parent))
		goto cleanup;

	if (cg_write(parent, "cgroup.subtree_control", "+cpu"))
		goto cleanup;

	if (cg_create(child))
		goto cleanup;

	if (cg_write(parent, "cpu.max", "1000"))
		goto cleanup;

	struct cpu_hog_func_param param = {
		.nprocs = 1,
		.ts = {
			.tv_sec = usage_seconds,
			.tv_nsec = 0,
		},
		.clock_type = CPU_HOG_CLOCK_WALL,
	};
	if (cg_run(child, hog_cpus_timed, (void *)&param))
		goto cleanup;

	usage_usec = cg_read_key_long(child, "cpu.stat", "usage_usec");
	user_usec = cg_read_key_long(child, "cpu.stat", "user_usec");
	if (user_usec <= 0)
		goto cleanup;

	if (user_usec >= expected_usage_usec)
		goto cleanup;

	if (values_close(usage_usec, expected_usage_usec, 95))
		goto cleanup;

	ret = KSFT_PASS;

cleanup:
	cg_destroy(child);
	free(child);
	cg_destroy(parent);
	free(parent);

	return ret;
}

#define T(x) { x, #x }
struct cpucg_test {
	int (*fn)(const char *root);
	const char *name;
} tests[] = {
	T(test_cpucg_subtree_control),
	T(test_cpucg_stats),
	T(test_cpucg_weight_overprovisioned),
	T(test_cpucg_weight_underprovisioned),
	T(test_cpucg_nested_weight_overprovisioned),
	T(test_cpucg_nested_weight_underprovisioned),
	T(test_cpucg_max),
	T(test_cpucg_max_nested),
};
#undef T

int main(int argc, char *argv[])
{
	char root[PATH_MAX];
	int i, ret = EXIT_SUCCESS;

	if (cg_find_unified_root(root, sizeof(root), NULL))
		ksft_exit_skip("cgroup v2 isn't mounted\n");

	if (cg_read_strstr(root, "cgroup.subtree_control", "cpu"))
		if (cg_write(root, "cgroup.subtree_control", "+cpu"))
			ksft_exit_skip("Failed to set cpu controller\n");

	for (i = 0; i < ARRAY_SIZE(tests); i++) {
		switch (tests[i].fn(root)) {
		case KSFT_PASS:
			ksft_test_result_pass("%s\n", tests[i].name);
			break;
		case KSFT_SKIP:
			ksft_test_result_skip("%s\n", tests[i].name);
			break;
		default:
			ret = EXIT_FAILURE;
			ksft_test_result_fail("%s\n", tests[i].name);
			break;
		}
	}

	return ret;
}