RFC Hot page promotion optimization for large address space
Get series with b4
b4 am [email protected]Versions newest first
- v1 RFC Latest2 patches 16 repliesIn review
Patches in v1 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/2 | sched/numa: Fault count based NUMA hint fault latencyinclude/ include/ kernel/ +5 more | +37 | 3 replies | |
| 2/2 | mm: Update hint fault count for pages that are skipped during scanningmm/ mm/ | +9 | 0 replies |
Reviews trailers per patch
No Reviewed-by, Acked-by or Tested-by trailers for v1 yet.
Cover letter [RFC PATCH 0/2] Hot page promotion optimization for large address space
In order to check how efficiently the existing NUMA balancing based hot page promotion mechanism can detect hot regions and promote pages for workloads with large memory footprints, I wrote and tested a program that allocates huge amount of memory but routinely touches only small parts of it.
This microbenchmark provisions memory both on DRAM node and CXL node. It then divides the entire allocated memory into chunks of smaller size and randomly choses a chunk for generating memory accesses. Each chunk is then accessed for a fixed number of iterations to create the notion of hotness. Within each chunk, the individual pages at 4K granularity are again accessed in random fashion.
When a chunk is taken up for access in this manner, its pages can either be residing on DRAM or CXL. In the latter case, the NUMA balancing driven hot page promotion logic is expected to detect and promote the hot pages that reside on CXL.
The experiment was conducted on a 2P AMD Bergamo system that has CXL as the 3rd node.
$ numactl -H available: 3 nodes (0-2) node 0 cpus: 0-127,256-383 node 0 size: 128054 MB node 1 cpus: 128-255,384-511 node 1 size: 128880 MB node 2 cpus: node 2 size: 129024 MB node distances: node 0 1 2 0: 10 32 60 1: 32 10 50 2: 255 255 10
It is seen that number of pages that get promoted is really low and the reason for it happens to be that the NUMA hint fault latency turns out to be much higher than the hot threshold most of the times. Here are a few latency and threshold sample values captured from should_numa_migrate_memory() routine when the benchmark was run:
latency threshold (in ms)
20620 1125
56185 1125
98710 1250
148871 1375
182891 1625
369415 1875
630745 2000
The NUMA hint fault latency metric, which is based on absolute time difference between scanning time and fault time may not be suitable for applications that have large amounts of memory. If the time difference between the scan time PTE update and the subsequent access (hint fault) is more, the existing logic in should_numa_migrate_memory() to determine if the page needs to be migrated, will exclude more pages than it selects pages for promotion.
To address this problem, this RFC converts the absolute time based hint fault latency in to a relative metric. The number of hint faults that have occurred between the scan time and the page's fault time is used as the threshold.
This is quite an experimental work and there are things to take care of still. While more testing needs to be conducted with different benchmarks, I am posting the patchset here to just get early feedback.
Microbenchmark
==============
Total allocation is 192G which initially occupies full of Node 1 (DRAM) and half of Node 2 (CXL)
Chunk size is 1G
Default Patched
Benchmark score (us) 637,787,351 571,350,410 (-10.41%)
(Lesser is better)
numa_pte_updates 29,834,747 29,275,489numa_hint_faults 12,512,736 12,080,772numa_hint_faults_local 0 0numa_pages_migrated 1,804,583 6,709,580pgpromote_success 1,804,500 6,709,526pgpromote_candidate 1,916,720 7,523,345pgdemote_kswapd 5,358,119 9,438,006pgdemote_direct 0 0
Default Patched
Number of timesshould_numa_migrate_memory()
was invoked: 12,512,736 12,080,772
Number of times the migration
request was rejected due to
hint fault latency being
higher than threshold: 10,595,933 4,557,401
Redis-memtier
=============memtier_benchmark -t 512 -n 25000 --ratio 1:1 -c 20 -x 1 --key-pattern R:R --hide-histogram --distinct-client-seed -d 20000 --pipeline=1000
Default Patched
Ops/sec 51,921.16 52,694.55
Hits/sec 21,908.72 22,235.03
Misses/sec 4051.86 4112.24
Avg. Latency 867.51710 591.27561 (-31.84%)
p50 Latency 876.54300 708.60700 (-19.15%)
p99 Latency 1044.47900 1044.47900
p99.9 Latency 1048.57500 1048.57500
KB/sec 937,330.19 951,291.76
numa_pte_updates 66,628,064 72,125,512numa_hint_faults 57,093,369 63,369,538numa_hint_faults_local 0 0numa_pages_migrated 799,128 3,634,114pgpromote_success 798,974 3,633,672pgpromote_candidate 33,884,196 23,143,552pgdemote_kswapd 13,321,784 11,948,894pgdemote_direct 257 57,147
Bharata B Rao (2):
sched/numa: Fault count based NUMA hint fault latency
mm: Update hint fault count for pages that are skipped during scanning
include/linux/mm.h | 23 ++++--------- include/linux/mm_types.h | 3 ++ kernel/sched/debug.c | 2 +- kernel/sched/fair.c | 73 +++++++++++----------------------------- kernel/sched/sched.h | 1 + mm/huge_memory.c | 10 +++--- mm/memory.c | 2 ++ mm/mprotect.c | 14 ++++---- 8 files changed, 46 insertions(+), 82 deletions(-)
Signature · 1 line
2.25.1