Skip to content

memcg: optimize charge codepath

Shakeel Butt cgroups linux-mm lkml netdev oe-lkp 2 versions – Applied

Status from this message: [merged mm-stable] memcg-increase-memcg_charge_batch-to-64.patch removed from -mm tree

Get series with b4
b4 am [email protected]

Versions newest first · linked by author and title

  1. v2 Latest3 patches 9 repliesApplied 3/3
  2. v13 patches 29 repliesSuperseded

Changes in v2 from the cover letter

- Commit message updates
- Instead of explicit padding add align compiler option with struct

Patches in v2 All 3 applied

#Subject and filesSizeRepliesApplied
1/3mm: page_counter: remove unneeded atomic ops for low/minmm/page_counter.c+6 -71 replyApplied
2/3mm: page_counter: rearrange struct page_counter fieldsinclude/linux/page_counter.h+23 -126 repliesApplied
3/3memcg: increase MEMCG_CHARGE_BATCH to 64include/linux/memcontrol.h+4 -32 repliesApplied

Reviews trailers per patch

All 3 patches have a Reviewed-by or Acked-by.

PatchSoheil Hassas YeganehFeng TangRoman GushchinMichal HockoMuchun Song
1/3A-b R-b A-b A-b
2/3A-b R-b A-b A-b
3/3A-b R-b A-b A-b A-b

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes. Scroll the table sideways for all 5 reviewers.

Read the v2 thread

Cover letter [PATCH v2 0/3] memcg: optimize charge codepath

Recently Linux networking stack has moved from a very old per socket pre-charge caching to per-cpu caching to avoid pre-charge fragmentation and unwarranted OOMs. One impact of this change is that for network traffic workloads, memcg charging codepath can become a bottleneck. The kernel test robot has also reported this regression[1]. This patch series tries to improve the memcg charging for such workloads.

This patch series implement three optimizations:
(A) Reduce atomic ops in page counter update path.
(B) Change layout of struct page_counter to eliminate false sharing between usage and high.
(C) Increase the memcg charge batch to 64.

To evaluate the impact of these optimizations, on a 72 CPUs machine, we ran the following workload in root memcg and then compared with scenario where the workload is run in a three level of cgroup hierarchy with top level having min and low setup appropriately.

 $ netserver -6
 # 36 instances of netperf with following params
 $ netperf -6 -H ::1 -l 60 -t TCP_SENDFILE -- -m 10K

Results (average throughput of netperf):
1. root memcg 21694.8 Mbps
2. 6.0-rc1 10482.7 Mbps (-51.6%)
3. 6.0-rc1 + (A) 14542.5 Mbps (-32.9%)
4. 6.0-rc1 + (B) 12413.7 Mbps (-42.7%)
5. 6.0-rc1 + (C) 17063.7 Mbps (-21.3%)
6. 6.0-rc1 + (A+B+C) 20120.3 Mbps (-7.2%)

With all three optimizations, the memcg overhead of this workload has been reduced from 51.6% to just 7.2%.

[1] https://lore.kernel.org/linux-mm/20220619150456.GB34471@xsang-OptiPlex-9020/

Changes since v1:
- Commit message updates
- Instead of explicit padding add align compiler option with struct

Shakeel Butt (3):
mm: page_counter: remove unneeded atomic ops for low/min
mm: page_counter: rearrange struct page_counter fields
memcg: increase MEMCG_CHARGE_BATCH to 64

 include/linux/memcontrol.h   |  7 ++++---
 include/linux/page_counter.h | 34 +++++++++++++++++++++++-----------
 mm/page_counter.c            | 13 ++++++-------
 3 files changed, 33 insertions(+), 21 deletions(-)
Signature · 1 line
2.37.1.595.g718a3a8f04-goog