Markk116/smarm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
3da6ffaa77c652d4a42cd1c60c892d93dbccb50f
smarm/benches/baseline-output/sweep/ai128_tc600k.txt
Bench 3da6ffaa77 benches: expose preemption knobs + sweep runner 
Config API changes (src/preempt.rs, src/runtime.rs):
- preempt: promote ALLOC_INTERVAL and TIMESLICE_CYCLES from bare consts to
  DEFAULT_ALLOC_INTERVAL / DEFAULT_TIMESLICE_CYCLES; store active values in
  thread-locals set on each actor resume so multiple runtimes can use
  different settings concurrently.
- runtime: add alloc_interval / timeslice_cycles fields to Config; add
  Config::alloc_interval(n) and Config::timeslice_cycles(c) builder methods;
  thread the values through RuntimeInner to the reset_timeslice() call in
  schedule_loop.

Bench changes:
- Add bench_cfg(threads) helper to general/tokio_favored/smarm_favored that
  wraps Config::exact and reads SMARM_ALLOC_INTERVAL / SMARM_TIMESLICE_CYCLES
  env vars, so the sweep script can vary knobs without recompiling.

Sweep tooling (benches/sweep.py):
- 'run':     run the 3-file bench suite once; --save-baseline persists JSON
- 'regress': compare current run against baseline.json, exit 1 on any bench
             that regresses >10% vs stored medians
- 'sweep':   run the full SWEEP_GRID (10 points), print comparison table,
             optional --save-csv; binaries pre-built so no recompile per point

Sweep results (10-point grid, 1-CPU sandbox):
- The preemption knobs have very little effect on this single-CPU machine.
  Most benches move <5% across the entire grid.
- Longer timeslices (tc=600k, tc=1200k) reliably hurt spawn_storm_busy
  (+11-15%) and catch_unwind_panics (+10-12%) because actors hold the
  scheduler mutex longer per timeslice, stalling the storm of joinable tasks.
- Shorter timeslices (tc=150k) give a small improvement on many_timers
  (-3-4%) and a wash everywhere else.
- yield_in_hot_loop and uncontended_channel are essentially flat across all
  knobs — both are scheduling-dominated and call yield_now explicitly, so
  the RDTSC-driven preemption path is irrelevant.
- Conclusion: the knobs matter primarily under contention (multi-core).
  Re-run sweep on a multi-core machine before drawing tuning conclusions.
2026-05-25 13:04:58 +00:00

127 lines
8.3 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

smarm general benchmarks
available parallelism: 1 threads
ITERS=15 (+1 warmup, discarded)
CHAIN_DEPTH=1000, YIELD_TASKS=200×1000, PRIME_N=400000/64 workers, PP_ROUNDS=1000
================================================================================
chained_spawn: depth 1000
================================================================================
runtime | result | median µs | min µs | max µs
--------------------------------------------------------------------------------
smarm 1-thread | 1000 | 8721 | 8398 | 8994
smarm 1-thread | 1000 | 8587 | 8440 | 8810
tokio current_thread | 1000 | 124 | 124 | 294
tokio multi-thread | 1000 | 188 | 184 | 299
================================================================================
yield_many: 200 tasks × 1000 yields
================================================================================
runtime | result | median µs | min µs | max µs
--------------------------------------------------------------------------------
smarm 1-thread | 200000 | 42588 | 42084 | 45080
smarm 1-thread | 200000 | 42252 | 41963 | 43615
tokio current_thread | 200000 | 15101 | 14994 | 15573
tokio multi-thread | 200000 | 15979 | 15890 | 16356
================================================================================
fan_out_compute: primes in [2, 400000) across 64
================================================================================
runtime | result | median µs | min µs | max µs
--------------------------------------------------------------------------------
smarm 1-thread | 33860 | 29686 | 29491 | 31263
smarm 1-thread | 33860 | 29841 | 29586 | 30570
tokio current_thread | 33860 | 28652 | 28510 | 30359
tokio multi-thread | 33860 | 34677 | 34461 | 35318
================================================================================
ping_pong_oneshot: 1000 rounds
================================================================================
runtime | result | median µs | min µs | max µs
--------------------------------------------------------------------------------
smarm 1-thread | 1000 | 16909 | 16579 | 20782
smarm 1-thread | 1000 | 16888 | 16537 | 20808
tokio current_thread | 1000 | 925 | 911 | 1021
tokio multi-thread | 1000 | 4192 | 4079 | 4531
smarm tokio-favored benchmarks
available parallelism: 1 threads
ITERS=15 (+1 warmup, discarded)
STORM_BACKGROUND=8, STORM_SPAWN=10000, MPSC=32×10000, TIMER_ACTORS=10000 (1–10 ms), SCALING_N=400000/64
================================================================================
spawn_storm_busy: 8 bg yielders + 10000 zero-work spawns
================================================================================
runtime | result | median µs | min µs | max µs
--------------------------------------------------------------------------------
smarm 1-thread | 10000 | 145813 | 142042 | 152501
smarm 1-thread | 10000 | 145119 | 141282 | 161294
tokio current_thread | 10000 | 2968 | 2899 | 3231
tokio multi-thread | 10000 | 6288 | 4289 | 12226
================================================================================
mpsc_contention: 32 producers × 10000 msgs → 1 consumer
================================================================================
runtime | result | median µs | min µs | max µs
--------------------------------------------------------------------------------
smarm 1-thread | 320000 | 9662 | 9254 | 11370
smarm 1-thread | 320000 | 9673 | 9331 | 9989
tokio current_thread | 320000 | 18015 | 17334 | 21096
tokio multi-thread | 320000 | 18384 | 17837 | 19534
================================================================================
many_timers: 10000 actors sleeping 1–10 ms
================================================================================
runtime | result | median µs | min µs | max µs
--------------------------------------------------------------------------------
smarm 1-thread | 10000 | 160492 | 154795 | 180307
smarm 1-thread | 10000 | 161716 | 156498 | 191986
tokio current_thread | 10000 | 13895 | 13576 | 14913
tokio multi-thread | 10000 | 15074 | 14665 | 16070
================================================================================
multi_thread_scaling: primes in [2, 400000) across 64 workers
================================================================================
runtime | result | median µs | min µs | max µs
--------------------------------------------------------------------------------
smarm 1-thread | 33860 | 30001 | 29600 | 38039
tokio multi 1-thread | 33860 | 29419 | 28906 | 30079
smarm smarm-favored benchmarks
available parallelism: 1 threads
ITERS=15 (+1 warmup, discarded)
RECURSE_DEPTH=500, HOT_YIELDS=500000×2, UNCONT_MSGS=1000000, PANIC_TASKS=10000
================================================================================
deep_recursion: depth 500
================================================================================
runtime | result | median µs | min µs | max µs
--------------------------------------------------------------------------------
smarm 1-thread | 1 | 91 | 79 | 186
smarm 1-thread | 1 | 87 | 81 | 131
tokio current_thread | 1 | 25 | 25 | 103
tokio multi-thread | 1 | 56 | 47 | 64
================================================================================
yield_in_hot_loop: 2 actors × 500000 yields (single thread)
================================================================================
runtime | result | median µs | min µs | max µs
--------------------------------------------------------------------------------
smarm 1-thread | 1000000 | 190023 | 188250 | 193824
tokio current_thread | 1000000 | 154681 | 152074 | 187328
================================================================================
uncontended_channel: 1→1, 1000000 msgs (single thread)
================================================================================
runtime | result | median µs | min µs | max µs
--------------------------------------------------------------------------------
smarm 1-thread | 1000000 | 27264 | 26772 | 29512
tokio current_thread | 1000000 | 53324 | 51744 | 59282
================================================================================
catch_unwind_panics: 10000 tasks, 50% panic
================================================================================
runtime | result | median µs | min µs | max µs
--------------------------------------------------------------------------------
smarm 1-thread | 10000 | 155983 | 152595 | 161438
smarm 1-thread | 10000 | 162122 | 156170 | 200357
tokio current_thread | 10000 | 276303 | 264291 | 296266
tokio multi-thread | 10000 | 271350 | 267654 | 285897
Reference in New Issue View Git Blame Copy Permalink