| From: |
| Shakeel Butt <shakeelb-AT-google.com> |
| To: |
| Johannes Weiner <hannes-AT-cmpxchg.org>, Michal Hocko <mhocko-AT-kernel.org>, Roman Gushchin <roman.gushchin-AT-linux.dev>, Muchun Song <songmuchun-AT-bytedance.com> |
| Subject: |
| [PATCH v2 0/3] memcg: optimize charge codepath |
| Date: |
| Thu, 25 Aug 2022 00:05:03 +0000 |
| Message-ID: |
| <20220825000506.239406-1-shakeelb@google.com> |
| Cc: |
| "Michal Koutný" <mkoutny-AT-suse.com>, Eric Dumazet <edumazet-AT-google.com>, Soheil Hassas Yeganeh <soheil-AT-google.com>, Feng Tang <feng.tang-AT-intel.com>, Oliver Sang <oliver.sang-AT-intel.com>, Andrew Morton <akpm-AT-linux-foundation.org>, lkp-AT-lists.01.org, cgroups-AT-vger.kernel.org, linux-mm-AT-kvack.org, netdev-AT-vger.kernel.org, linux-kernel-AT-vger.kernel.org, Shakeel Butt <shakeelb-AT-google.com> |
| Archive-link: |
| Article |
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@x...
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(-)
--
2.37.1.595.g718a3a8f04-goog
