LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Roman Gushchin <guro@fb.com>
To: Andrew Morton <akpm@linux-foundation.org>,
	Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>,
	Michal Hocko <mhocko@kernel.org>,
	Shakeel Butt <shakeelb@google.com>, <linux-mm@kvack.org>,
	Vlastimil Babka <vbabka@suse.cz>, <kernel-team@fb.com>,
	<linux-kernel@vger.kernel.org>, Roman Gushchin <guro@fb.com>
Subject: [PATCH v6 18/19] kselftests: cgroup: add kernel memory accounting tests
Date: Mon, 8 Jun 2020 16:06:53 -0700
Message-ID: <20200608230654.828134-19-guro@fb.com> (raw)
In-Reply-To: <20200608230654.828134-1-guro@fb.com>

Add some tests to cover the kernel memory accounting functionality.
These are covering some issues (and changes) we had recently.

1) A test which allocates a lot of negative dentries, checks memcg
slab statistics, creates memory pressure by setting memory.max
to some low value and checks that some number of slabs was reclaimed.

2) A test which covers side effects of memcg destruction: it creates
and destroys a large number of sub-cgroups, each containing a
multi-threaded workload which allocates and releases some kernel
memory. Then it checks that the charge ans memory.stats do add up
on the parent level.

3) A test which reads /proc/kpagecgroup and implicitly checks that it
doesn't crash the system.

4) A test which spawns a large number of threads and checks that
the kernel stacks accounting works as expected.

5) A test which checks that living charged slab objects are not
preventing the memory cgroup from being released after being deleted
by a user.

Signed-off-by: Roman Gushchin <guro@fb.com>
---
 tools/testing/selftests/cgroup/.gitignore  |   1 +
 tools/testing/selftests/cgroup/Makefile    |   2 +
 tools/testing/selftests/cgroup/test_kmem.c | 382 +++++++++++++++++++++
 3 files changed, 385 insertions(+)
 create mode 100644 tools/testing/selftests/cgroup/test_kmem.c

diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore
index aa6de65b0838..84cfcabea838 100644
--- a/tools/testing/selftests/cgroup/.gitignore
+++ b/tools/testing/selftests/cgroup/.gitignore
@@ -2,3 +2,4 @@
 test_memcontrol
 test_core
 test_freezer
+test_kmem
\ No newline at end of file
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
index 967f268fde74..f027d933595b 100644
--- a/tools/testing/selftests/cgroup/Makefile
+++ b/tools/testing/selftests/cgroup/Makefile
@@ -6,11 +6,13 @@ all:
 TEST_FILES     := with_stress.sh
 TEST_PROGS     := test_stress.sh
 TEST_GEN_PROGS = test_memcontrol
+TEST_GEN_PROGS += test_kmem
 TEST_GEN_PROGS += test_core
 TEST_GEN_PROGS += test_freezer
 
 include ../lib.mk
 
 $(OUTPUT)/test_memcontrol: cgroup_util.c ../clone3/clone3_selftests.h
+$(OUTPUT)/test_kmem: cgroup_util.c ../clone3/clone3_selftests.h
 $(OUTPUT)/test_core: cgroup_util.c ../clone3/clone3_selftests.h
 $(OUTPUT)/test_freezer: cgroup_util.c ../clone3/clone3_selftests.h
diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
new file mode 100644
index 000000000000..5224dae216e5
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -0,0 +1,382 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <linux/limits.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <sys/wait.h>
+#include <errno.h>
+#include <sys/sysinfo.h>
+#include <pthread.h>
+
+#include "../kselftest.h"
+#include "cgroup_util.h"
+
+
+static int alloc_dcache(const char *cgroup, void *arg)
+{
+	unsigned long i;
+	struct stat st;
+	char buf[128];
+
+	for (i = 0; i < (unsigned long)arg; i++) {
+		snprintf(buf, sizeof(buf),
+			"/something-non-existent-with-a-long-name-%64lu-%d",
+			 i, getpid());
+		stat(buf, &st);
+	}
+
+	return 0;
+}
+
+/*
+ * This test allocates 100000 of negative dentries with long names.
+ * Then it checks that "slab" in memory.stat is larger than 1M.
+ * Then it sets memory.high to 1M and checks that at least 1/2
+ * of slab memory has been reclaimed.
+ */
+static int test_kmem_basic(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cg = NULL;
+	long slab0, slab1, current;
+
+	cg = cg_name(root, "kmem_basic_test");
+	if (!cg)
+		goto cleanup;
+
+	if (cg_create(cg))
+		goto cleanup;
+
+	if (cg_run(cg, alloc_dcache, (void *)100000))
+		goto cleanup;
+
+	slab0 = cg_read_key_long(cg, "memory.stat", "slab ");
+	if (slab0 < (1 << 20))
+		goto cleanup;
+
+	cg_write(cg, "memory.high", "1M");
+	slab1 = cg_read_key_long(cg, "memory.stat", "slab ");
+	if (slab1 <= 0)
+		goto cleanup;
+
+	current = cg_read_long(cg, "memory.current");
+	if (current <= 0)
+		goto cleanup;
+
+	if (slab1 < slab0 / 2 && current < slab0 / 2)
+		ret = KSFT_PASS;
+cleanup:
+	cg_destroy(cg);
+	free(cg);
+
+	return ret;
+}
+
+static void *alloc_kmem_fn(void *arg)
+{
+	alloc_dcache(NULL, (void *)100);
+	return NULL;
+}
+
+static int alloc_kmem_smp(const char *cgroup, void *arg)
+{
+	int nr_threads = 2 * get_nprocs();
+	pthread_t *tinfo;
+	unsigned long i;
+	int ret = -1;
+
+	tinfo = calloc(nr_threads, sizeof(pthread_t));
+	if (tinfo == NULL)
+		return -1;
+
+	for (i = 0; i < nr_threads; i++) {
+		if (pthread_create(&tinfo[i], NULL, &alloc_kmem_fn,
+				   (void *)i)) {
+			free(tinfo);
+			return -1;
+		}
+	}
+
+	for (i = 0; i < nr_threads; i++) {
+		ret = pthread_join(tinfo[i], NULL);
+		if (ret)
+			break;
+	}
+
+	free(tinfo);
+	return ret;
+}
+
+static int cg_run_in_subcgroups(const char *parent,
+				int (*fn)(const char *cgroup, void *arg),
+				void *arg, int times)
+{
+	char *child;
+	int i;
+
+	for (i = 0; i < times; i++) {
+		child = cg_name_indexed(parent, "child", i);
+		if (!child)
+			return -1;
+
+		if (cg_create(child)) {
+			cg_destroy(child);
+			free(child);
+			return -1;
+		}
+
+		if (cg_run(child, fn, NULL)) {
+			cg_destroy(child);
+			free(child);
+			return -1;
+		}
+
+		cg_destroy(child);
+		free(child);
+	}
+
+	return 0;
+}
+
+/*
+ * The test creates and destroys a large number of cgroups. In each cgroup it
+ * allocates some slab memory (mostly negative dentries) using 2 * NR_CPUS
+ * threads. Then it checks the sanity of numbers on the parent level:
+ * the total size of the cgroups should be roughly equal to
+ * anon + file + slab + kernel_stack.
+ */
+static int test_kmem_memcg_deletion(const char *root)
+{
+	long current, slab, anon, file, kernel_stack, sum;
+	int ret = KSFT_FAIL;
+	char *parent;
+
+	parent = cg_name(root, "kmem_memcg_deletion_test");
+	if (!parent)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_run_in_subcgroups(parent, alloc_kmem_smp, NULL, 100))
+		goto cleanup;
+
+	current = cg_read_long(parent, "memory.current");
+	slab = cg_read_key_long(parent, "memory.stat", "slab ");
+	anon = cg_read_key_long(parent, "memory.stat", "anon ");
+	file = cg_read_key_long(parent, "memory.stat", "file ");
+	kernel_stack = cg_read_key_long(parent, "memory.stat", "kernel_stack ");
+	if (current < 0 || slab < 0 || anon < 0 || file < 0 ||
+	    kernel_stack < 0)
+		goto cleanup;
+
+	sum = slab + anon + file + kernel_stack;
+	if (abs(sum - current) < 4096 * 32 * 2 * get_nprocs()) {
+		ret = KSFT_PASS;
+	} else {
+		printf("memory.current = %ld\n", current);
+		printf("slab + anon + file + kernel_stack = %ld\n", sum);
+		printf("slab = %ld\n", slab);
+		printf("anon = %ld\n", anon);
+		printf("file = %ld\n", file);
+		printf("kernel_stack = %ld\n", kernel_stack);
+	}
+
+cleanup:
+	cg_destroy(parent);
+	free(parent);
+
+	return ret;
+}
+
+/*
+ * The test reads the entire /proc/kpagecgroup. If the operation went
+ * successfully (and the kernel didn't panic), the test is treated as passed.
+ */
+static int test_kmem_proc_kpagecgroup(const char *root)
+{
+	unsigned long buf[128];
+	int ret = KSFT_FAIL;
+	ssize_t len;
+	int fd;
+
+	fd = open("/proc/kpagecgroup", O_RDONLY);
+	if (fd < 0)
+		return ret;
+
+	do {
+		len = read(fd, buf, sizeof(buf));
+	} while (len > 0);
+
+	if (len == 0)
+		ret = KSFT_PASS;
+
+	close(fd);
+	return ret;
+}
+
+static void *pthread_wait_fn(void *arg)
+{
+	sleep(100);
+	return NULL;
+}
+
+static int spawn_1000_threads(const char *cgroup, void *arg)
+{
+	int nr_threads = 1000;
+	pthread_t *tinfo;
+	unsigned long i;
+	long stack;
+	int ret = -1;
+
+	tinfo = calloc(nr_threads, sizeof(pthread_t));
+	if (tinfo == NULL)
+		return -1;
+
+	for (i = 0; i < nr_threads; i++) {
+		if (pthread_create(&tinfo[i], NULL, &pthread_wait_fn,
+				   (void *)i)) {
+			free(tinfo);
+			return(-1);
+		}
+	}
+
+	stack = cg_read_key_long(cgroup, "memory.stat", "kernel_stack ");
+	if (stack >= 4096 * 1000)
+		ret = 0;
+
+	free(tinfo);
+	return ret;
+}
+
+/*
+ * The test spawns a process, which spawns 1000 threads. Then it checks
+ * that memory.stat's kernel_stack is at least 1000 pages large.
+ */
+static int test_kmem_kernel_stacks(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cg = NULL;
+
+	cg = cg_name(root, "kmem_kernel_stacks_test");
+	if (!cg)
+		goto cleanup;
+
+	if (cg_create(cg))
+		goto cleanup;
+
+	if (cg_run(cg, spawn_1000_threads, NULL))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+cleanup:
+	cg_destroy(cg);
+	free(cg);
+
+	return ret;
+}
+
+/*
+ * This test sequentionally creates 30 child cgroups, allocates some
+ * kernel memory in each of them, and deletes them. Then it checks
+ * that the number of dying cgroups on the parent level is 0.
+ */
+static int test_kmem_dead_cgroups(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent;
+	long dead;
+	int i;
+
+	parent = cg_name(root, "kmem_dead_cgroups_test");
+	if (!parent)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_run_in_subcgroups(parent, alloc_dcache, (void *)100, 30))
+		goto cleanup;
+
+	for (i = 0; i < 5; i++) {
+		dead = cg_read_key_long(parent, "cgroup.stat",
+					"nr_dying_descendants ");
+		if (dead == 0) {
+			ret = KSFT_PASS;
+			break;
+		}
+		/*
+		 * Reclaiming cgroups might take some time,
+		 * let's wait a bit and repeat.
+		 */
+		sleep(1);
+	}
+
+cleanup:
+	cg_destroy(parent);
+	free(parent);
+
+	return ret;
+}
+
+#define T(x) { x, #x }
+struct kmem_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_kmem_basic),
+	T(test_kmem_memcg_deletion),
+	T(test_kmem_proc_kpagecgroup),
+	T(test_kmem_kernel_stacks),
+	T(test_kmem_dead_cgroups),
+};
+#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)))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+	/*
+	 * Check that memory controller is available:
+	 * memory is listed in cgroup.controllers
+	 */
+	if (cg_read_strstr(root, "cgroup.controllers", "memory"))
+		ksft_exit_skip("memory controller isn't available\n");
+
+	if (cg_read_strstr(root, "cgroup.subtree_control", "memory"))
+		if (cg_write(root, "cgroup.subtree_control", "+memory"))
+			ksft_exit_skip("Failed to set memory 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;
+}
-- 
2.25.4


  parent reply index

Thread overview: 92+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-08 23:06 [PATCH v6 00/19] The new cgroup slab memory controller Roman Gushchin
2020-06-08 23:06 ` [PATCH v6 01/19] mm: memcg: factor out memcg- and lruvec-level changes out of __mod_lruvec_state() Roman Gushchin
2020-06-17  1:52   ` Shakeel Butt
2020-06-17  2:50     ` Roman Gushchin
2020-06-17  2:59       ` Shakeel Butt
2020-06-17  3:19         ` Roman Gushchin
2020-06-08 23:06 ` [PATCH v6 02/19] mm: memcg: prepare for byte-sized vmstat items Roman Gushchin
2020-06-17  2:57   ` Shakeel Butt
2020-06-17  3:19     ` Roman Gushchin
2020-06-17 15:55   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 03/19] mm: memcg: convert vmstat slab counters to bytes Roman Gushchin
2020-06-17  3:03   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 04/19] mm: slub: implement SLUB version of obj_to_index() Roman Gushchin
2020-06-17  3:08   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 05/19] mm: memcontrol: decouple reference counting from page accounting Roman Gushchin
2020-06-18  0:47   ` Shakeel Butt
2020-06-18 14:55   ` Shakeel Butt
2020-06-18 19:51     ` Roman Gushchin
2020-06-19  1:08     ` Roman Gushchin
2020-06-19  1:18       ` Shakeel Butt
2020-06-19  1:31   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 06/19] mm: memcg/slab: obj_cgroup API Roman Gushchin
2020-06-19 15:42   ` Shakeel Butt
2020-06-19 21:38     ` Roman Gushchin
2020-06-19 22:16       ` Shakeel Butt
2020-06-19 22:52         ` Roman Gushchin
2020-06-20 22:50       ` Andrew Morton
2020-06-08 23:06 ` [PATCH v6 07/19] mm: memcg/slab: allocate obj_cgroups for non-root slab pages Roman Gushchin
2020-06-19 16:36   ` Shakeel Butt
2020-06-20  0:25     ` Roman Gushchin
2020-06-20  0:31       ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 08/19] mm: memcg/slab: save obj_cgroup for non-root slab objects Roman Gushchin
2020-06-20  0:16   ` Shakeel Butt
2020-06-20  1:19     ` Roman Gushchin
2020-06-08 23:06 ` [PATCH v6 09/19] mm: memcg/slab: charge individual slab objects instead of pages Roman Gushchin
2020-06-20  0:54   ` Shakeel Butt
2020-06-20  1:29     ` Roman Gushchin
2020-06-08 23:06 ` [PATCH v6 10/19] mm: memcg/slab: deprecate memory.kmem.slabinfo Roman Gushchin
2020-06-22 17:12   ` Shakeel Butt
2020-06-22 18:01     ` Roman Gushchin
2020-06-22 18:09       ` Shakeel Butt
2020-06-22 18:25         ` Roman Gushchin
2020-06-22 18:38           ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 11/19] mm: memcg/slab: move memcg_kmem_bypass() to memcontrol.h Roman Gushchin
2020-06-20  1:19   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 12/19] mm: memcg/slab: use a single set of kmem_caches for all accounted allocations Roman Gushchin
2020-06-22 16:56   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 13/19] mm: memcg/slab: simplify memcg cache creation Roman Gushchin
2020-06-22 17:29   ` Shakeel Butt
2020-06-22 17:40     ` Roman Gushchin
2020-06-22 18:03       ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 14/19] mm: memcg/slab: remove memcg_kmem_get_cache() Roman Gushchin
2020-06-22 18:42   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 15/19] mm: memcg/slab: deprecate slab_root_caches Roman Gushchin
2020-06-22 17:36   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 16/19] mm: memcg/slab: remove redundant check in memcg_accumulate_slabinfo() Roman Gushchin
2020-06-22 17:32   ` Shakeel Butt
2020-06-08 23:06 ` [PATCH v6 17/19] mm: memcg/slab: use a single set of kmem_caches for all allocations Roman Gushchin
2020-06-17 23:35   ` Andrew Morton
2020-06-18  0:35     ` Roman Gushchin
2020-06-18  7:33       ` Vlastimil Babka
2020-06-18 19:54         ` Roman Gushchin
2020-06-22 19:21   ` Shakeel Butt
2020-06-22 20:37     ` Roman Gushchin
2020-06-22 21:04       ` Shakeel Butt
2020-06-22 21:13         ` Roman Gushchin
2020-06-22 21:28           ` Shakeel Butt
2020-06-22 21:58             ` Roman Gushchin
2020-06-22 22:05               ` Shakeel Butt
2020-06-08 23:06 ` Roman Gushchin [this message]
2020-06-17  1:46 ` [PATCH v6 00/19] The new cgroup slab memory controller Shakeel Butt
2020-06-17  2:41   ` Roman Gushchin
2020-06-17  3:05     ` Shakeel Butt
2020-06-17  3:32       ` Roman Gushchin
2020-06-17 11:24         ` Vlastimil Babka
2020-06-17 14:31           ` Mel Gorman
2020-06-20  0:57             ` Roman Gushchin
2020-06-18  1:29           ` Roman Gushchin
2020-06-18  8:43             ` Jesper Dangaard Brouer
2020-06-18  9:31               ` Jesper Dangaard Brouer
2020-06-19  1:30                 ` Roman Gushchin
2020-06-19  8:32                   ` Jesper Dangaard Brouer
2020-06-19  1:27               ` Roman Gushchin
2020-06-19  9:39                 ` Jesper Dangaard Brouer
2020-06-19 18:47                   ` Roman Gushchin
2020-06-18  1:18   ` Roman Gushchin
2020-06-18  9:27 ` Mike Rapoport
2020-06-18 20:43   ` Roman Gushchin
2020-06-21 22:57 ` Qian Cai
2020-06-21 23:34   ` Roman Gushchin
2020-06-21 23:53     ` Qian Cai
2020-06-22  3:07       ` Roman Gushchin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200608230654.828134-19-guro@fb.com \
    --to=guro@fb.com \
    --cc=akpm@linux-foundation.org \
    --cc=cl@linux.com \
    --cc=hannes@cmpxchg.org \
    --cc=kernel-team@fb.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=shakeelb@google.com \
    --cc=vbabka@suse.cz \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git