[PATCH v1 -next 0/3] Some optimizations about freezer

[Chen Ridong <chenridong@huawei.com>]

We optimized the freezer to reduce redundant loops. We add a selftest to
ensure our optimizations cause no harm, and we confirmed that the
performance can be improved.

We tested the following subtree: D, E, F and G each have n children.
        A
       / \
      B   C
    / | \  \
    D E F   G
   /  |  \   \
 1-n 1-n 1-n  0-n

Our test is to freeze A B C D E F G, and then unfreeze A B C D E F G.
We measured the elapsed time.

	BEFORE(ns)	AFTER(ns)	SAVED(ns)
n=10	142679950	139666014	3,013,936
n=100	199832160	192773032	7,059,128
n=1000	488595100	414901570	73,693,530

As shown above, the larger the value of n, the more significant the time
savings can be. If tested with a deeper hierarchy, the difference could
become even more apparent.

Chen Ridong (3):
  cgroup/freezer: Reduce redundant traversal for cgroup_freeze
  cgroup/freezer: Reduce redundant propagation for
    cgroup_propagate_frozen
  cgroup/freezer: Add freeze selftest

 include/linux/cgroup-defs.h                   |   2 +-
 kernel/cgroup/freezer.c                       |  72 ++++++++----
 .../testing/selftests/cgroup/test_freezer.sh  | 111 ++++++++++++++++++
 3 files changed, 160 insertions(+), 25 deletions(-)
 create mode 100755 tools/testing/selftests/cgroup/test_freezer.sh

-- 
2.34.1