mbox series

[v2,0/3] mm/ksm: cmp_and_merge_page() optimizations and cleanup

Message ID 20240621-b4-ksm-scan-optimize-v2-0-1c328aa9e30b@linux.dev (mailing list archive)
Headers show
Series mm/ksm: cmp_and_merge_page() optimizations and cleanup | expand

Message

Chengming Zhou June 21, 2024, 7:54 a.m. UTC 
Changes in v2:
- Fix the comments of try_to_merge_with_zero_page(), per David.
- Drop the last one patch in this version since it's a very rare case
  and hard to testing to prove.
- Rebase on the latest mm/mm-stable branch.
- Link to v1: https://lore.kernel.org/r/20240524-b4-ksm-scan-optimize-v1-0-053b31bd7ab4@linux.dev

Hello,

This series mainly optimizes cmp_and_merge_page() to have more efficient
separate code flow for ksm page and non-ksm anon page.

- ksm page: don't need to calculate the checksum obviously.
- anon page: don't need to search stable tree if changing fast and try
  to merge with zero page before searching ksm page on stable tree.

Please see the patch-2 for details.

Patch-3 is cleanup also a little optimization for the chain()/chain_prune
interfaces, which made the stable_tree_search()/stable_tree_insert() over
complex.

I have done simple testing using "hackbench -g 1 -l 300000" (maybe I need
to use a better workload) on my machine, have seen a little CPU usage
decrease of ksmd and some improvements of cmp_and_merge_page() latency:

We can see the latency of cmp_and_merge_page() when handling non-ksm
anon pages has been improved.

Thanks for review and comments!

Before:

- ksm page
[128, 256)            21 |                                                    |
[256, 512)         12509 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[512, 1K)            769 |@@@                                                 |
[1K, 2K)              99 |                                                    |
[2K, 4K)               4 |                                                    |
[4K, 8K)               2 |                                                    |
[8K, 16K)              8 |                                                    |

- anon page
[512, 1K)             19 |                                                    |
[1K, 2K)            7160 |@@@@@@@@@@@                                         |
[2K, 4K)           33516 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[4K, 8K)           33172 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[8K, 16K)          11305 |@@@@@@@@@@@@@@@@@                                   |
[16K, 32K)          1303 |@@                                                  |
[32K, 64K)            16 |                                                    |
[64K, 128K)            6 |                                                    |
[128K, 256K)           6 |                                                    |
[256K, 512K)           9 |                                                    |
[512K, 1M)             3 |                                                    |
[1M, 2M)               2 |                                                    |
[2M, 4M)               1 |                                                    |

After:

- ksm page
[128, 256)             9 |                                                    |
[256, 512)           915 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[512, 1K)             41 |@@                                                  |
[1K, 2K)               1 |                                                    |
[2K, 4K)               1 |                                                    |

- anon page
[512, 1K)            374 |                                                    |
[1K, 2K)            5367 |@@@@                                                |
[2K, 4K)           64362 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[4K, 8K)           27721 |@@@@@@@@@@@@@@@@@@@@@@                              |
[8K, 16K)           1047 |                                                    |
[16K, 32K)            63 |                                                    |
[32K, 64K)             7 |                                                    |
[64K, 128K)            6 |                                                    |
[128K, 256K)           5 |                                                    |
[256K, 512K)           3 |                                                    |
[512K, 1M)             1 |                                                    |

Signed-off-by: Chengming Zhou <chengming.zhou@linux.dev>
---
Chengming Zhou (3):
      mm/ksm: refactor out try_to_merge_with_zero_page()
      mm/ksm: don't waste time searching stable tree for fast changing page
      mm/ksm: optimize the chain()/chain_prune() interfaces

 mm/ksm.c | 250 +++++++++++++++++++++------------------------------------------
 1 file changed, 82 insertions(+), 168 deletions(-)
---
base-commit: 6ba59ff4227927d3a8530fc2973b80e94b54d58f
change-id: 20240621-b4-ksm-scan-optimize-e614a3a52217

Best regards,

Comments

Andrew Morton June 28, 2024, 11:59 p.m. UTC | #1 
On Fri, 21 Jun 2024 15:54:28 +0800 Chengming Zhou <chengming.zhou@linux.dev> wrote:

> This series mainly optimizes cmp_and_merge_page() to have more efficient
> separate code flow for ksm page and non-ksm anon page.

Is anyone interested in reviewing this patchset further?