Message ID | 20200528232508.1132382-6-guro@fb.com (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
Series | mm: memcg accounting of percpu memory | expand |
On Thu, May 28, 2020 at 04:25:08PM -0700, Roman Gushchin wrote: > Add a simple test to check the percpu memory accounting. > The test creates a cgroup tree with 1000 child cgroups > and checks values of memory.current and memory.stat::percpu. > > Signed-off-by: Roman Gushchin <guro@fb.com> > --- > tools/testing/selftests/cgroup/test_kmem.c | 59 ++++++++++++++++++++++ > 1 file changed, 59 insertions(+) > > diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c > index 5224dae216e5..a0d4f1a3137d 100644 > --- a/tools/testing/selftests/cgroup/test_kmem.c > +++ b/tools/testing/selftests/cgroup/test_kmem.c > @@ -331,6 +331,64 @@ static int test_kmem_dead_cgroups(const char *root) > return ret; > } > > +/* > + * This test creates a sub-tree with 1000 memory cgroups. > + * Then it checks that the memory.current on the parent level > + * is greater than 0 and approximates matches the percpu value > + * from memory.stat. > + */ > +static int test_percpu_basic(const char *root) > +{ > + int ret = KSFT_FAIL; > + char *parent, *child; > + long current, percpu; > + int i; > + > + parent = cg_name(root, "percpu_basic_test"); > + if (!parent) > + goto cleanup; > + > + if (cg_create(parent)) > + goto cleanup; > + > + if (cg_write(parent, "cgroup.subtree_control", "+memory")) > + goto cleanup; > + > + for (i = 0; i < 1000; i++) { > + child = cg_name_indexed(parent, "child", i); > + if (!child) > + return -1; > + > + if (cg_create(child)) > + goto cleanup_children; > + > + free(child); > + } > + > + current = cg_read_long(parent, "memory.current"); > + percpu = cg_read_key_long(parent, "memory.stat", "percpu "); > + > + if (current > 0 && percpu > 0 && abs(current - percpu) < > + 4096 * 32 * get_nprocs()) So this is checking that we've allocated less than 32 pages per cpu over 1000 child cgroups that's not percpu memory? Is there a more definitive measurement or at least a comment we can leave saying why this limit was chosen. > + ret = KSFT_PASS; > + else > + printf("memory.current %ld\npercpu %ld\n", > + current, percpu); > + > +cleanup_children: > + for (i = 0; i < 1000; i++) { > + child = cg_name_indexed(parent, "child", i); > + cg_destroy(child); > + free(child); > + } > + > +cleanup: > + cg_destroy(parent); > + free(parent); > + > + return ret; > +} > + > #define T(x) { x, #x } > struct kmem_test { > int (*fn)(const char *root); > @@ -341,6 +399,7 @@ struct kmem_test { > T(test_kmem_proc_kpagecgroup), > T(test_kmem_kernel_stacks), > T(test_kmem_dead_cgroups), > + T(test_percpu_basic), > }; > #undef T > > -- > 2.25.4 > >
On Fri, Jun 05, 2020 at 08:07:51PM +0000, Dennis Zhou wrote: > On Thu, May 28, 2020 at 04:25:08PM -0700, Roman Gushchin wrote: > > Add a simple test to check the percpu memory accounting. > > The test creates a cgroup tree with 1000 child cgroups > > and checks values of memory.current and memory.stat::percpu. > > > > Signed-off-by: Roman Gushchin <guro@fb.com> > > --- > > tools/testing/selftests/cgroup/test_kmem.c | 59 ++++++++++++++++++++++ > > 1 file changed, 59 insertions(+) > > > > diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c > > index 5224dae216e5..a0d4f1a3137d 100644 > > --- a/tools/testing/selftests/cgroup/test_kmem.c > > +++ b/tools/testing/selftests/cgroup/test_kmem.c > > @@ -331,6 +331,64 @@ static int test_kmem_dead_cgroups(const char *root) > > return ret; > > } > > > > +/* > > + * This test creates a sub-tree with 1000 memory cgroups. > > + * Then it checks that the memory.current on the parent level > > + * is greater than 0 and approximates matches the percpu value > > + * from memory.stat. > > + */ > > +static int test_percpu_basic(const char *root) > > +{ > > + int ret = KSFT_FAIL; > > + char *parent, *child; > > + long current, percpu; > > + int i; > > + > > + parent = cg_name(root, "percpu_basic_test"); > > + if (!parent) > > + goto cleanup; > > + > > + if (cg_create(parent)) > > + goto cleanup; > > + > > + if (cg_write(parent, "cgroup.subtree_control", "+memory")) > > + goto cleanup; > > + > > + for (i = 0; i < 1000; i++) { > > + child = cg_name_indexed(parent, "child", i); > > + if (!child) > > + return -1; > > + > > + if (cg_create(child)) > > + goto cleanup_children; > > + > > + free(child); > > + } > > + > > + current = cg_read_long(parent, "memory.current"); > > + percpu = cg_read_key_long(parent, "memory.stat", "percpu "); > > + > > + if (current > 0 && percpu > 0 && abs(current - percpu) < > > + 4096 * 32 * get_nprocs()) > > So this is checking that we've allocated less than 32 pages per cpu over > 1000 child cgroups that's not percpu memory? Is there a more definitive > measurement or at least a comment we can leave saying why this limit was > chosen. It simple means that "current" should be approximately equal to "percpu" statistics. Both charging and vmstat paths are using percpu batching, and the batch size is 32 pages. I'll add a comment to make it more obvious. Thanks! > > > + ret = KSFT_PASS; > > + else > > + printf("memory.current %ld\npercpu %ld\n", > > + current, percpu); > > + > > +cleanup_children: > > + for (i = 0; i < 1000; i++) { > > + child = cg_name_indexed(parent, "child", i); > > + cg_destroy(child); > > + free(child); > > + } > > + > > +cleanup: > > + cg_destroy(parent); > > + free(parent); > > + > > + return ret; > > +} > > + > > #define T(x) { x, #x } > > struct kmem_test { > > int (*fn)(const char *root); > > @@ -341,6 +399,7 @@ struct kmem_test { > > T(test_kmem_proc_kpagecgroup), > > T(test_kmem_kernel_stacks), > > T(test_kmem_dead_cgroups), > > + T(test_percpu_basic), > > }; > > #undef T > > > > -- > > 2.25.4 > > > >
diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index 5224dae216e5..a0d4f1a3137d 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -331,6 +331,64 @@ static int test_kmem_dead_cgroups(const char *root) return ret; } +/* + * This test creates a sub-tree with 1000 memory cgroups. + * Then it checks that the memory.current on the parent level + * is greater than 0 and approximates matches the percpu value + * from memory.stat. + */ +static int test_percpu_basic(const char *root) +{ + int ret = KSFT_FAIL; + char *parent, *child; + long current, percpu; + int i; + + parent = cg_name(root, "percpu_basic_test"); + if (!parent) + goto cleanup; + + if (cg_create(parent)) + goto cleanup; + + if (cg_write(parent, "cgroup.subtree_control", "+memory")) + goto cleanup; + + for (i = 0; i < 1000; i++) { + child = cg_name_indexed(parent, "child", i); + if (!child) + return -1; + + if (cg_create(child)) + goto cleanup_children; + + free(child); + } + + current = cg_read_long(parent, "memory.current"); + percpu = cg_read_key_long(parent, "memory.stat", "percpu "); + + if (current > 0 && percpu > 0 && abs(current - percpu) < + 4096 * 32 * get_nprocs()) + ret = KSFT_PASS; + else + printf("memory.current %ld\npercpu %ld\n", + current, percpu); + +cleanup_children: + for (i = 0; i < 1000; i++) { + child = cg_name_indexed(parent, "child", i); + cg_destroy(child); + free(child); + } + +cleanup: + cg_destroy(parent); + free(parent); + + return ret; +} + #define T(x) { x, #x } struct kmem_test { int (*fn)(const char *root); @@ -341,6 +399,7 @@ struct kmem_test { T(test_kmem_proc_kpagecgroup), T(test_kmem_kernel_stacks), T(test_kmem_dead_cgroups), + T(test_percpu_basic), }; #undef T
Add a simple test to check the percpu memory accounting. The test creates a cgroup tree with 1000 child cgroups and checks values of memory.current and memory.stat::percpu. Signed-off-by: Roman Gushchin <guro@fb.com> --- tools/testing/selftests/cgroup/test_kmem.c | 59 ++++++++++++++++++++++ 1 file changed, 59 insertions(+)