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 <g...@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
> >
> >
