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.
This commit is contained in:
Bench
126
benches/baseline-output/sweep/ai32_tc150k.txt
Normal file
126
benches/baseline-output/sweep/ai32_tc150k.txt
Normal file
@@ -0,0 +1,126 @@
|
||||
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 | 8653 | 8522 | 9163
|
||||
smarm 1-thread | 1000 | 8908 | 8660 | 10606
|
||||
tokio current_thread | 1000 | 124 | 123 | 175
|
||||
tokio multi-thread | 1000 | 244 | 184 | 340
|
||||
|
||||
================================================================================
|
||||
yield_many: 200 tasks × 1000 yields
|
||||
================================================================================
|
||||
runtime | result | median µs | min µs | max µs
|
||||
--------------------------------------------------------------------------------
|
||||
smarm 1-thread | 200000 | 42597 | 41857 | 43492
|
||||
smarm 1-thread | 200000 | 42621 | 42097 | 44386
|
||||
tokio current_thread | 200000 | 15368 | 15144 | 16484
|
||||
tokio multi-thread | 200000 | 16120 | 16012 | 19222
|
||||
|
||||
================================================================================
|
||||
fan_out_compute: primes in [2, 400000) across 64
|
||||
================================================================================
|
||||
runtime | result | median µs | min µs | max µs
|
||||
--------------------------------------------------------------------------------
|
||||
smarm 1-thread | 33860 | 30499 | 29657 | 33910
|
||||
smarm 1-thread | 33860 | 31190 | 30105 | 32675
|
||||
tokio current_thread | 33860 | 28748 | 28643 | 29398
|
||||
tokio multi-thread | 33860 | 34714 | 34499 | 36338
|
||||
|
||||
================================================================================
|
||||
ping_pong_oneshot: 1000 rounds
|
||||
================================================================================
|
||||
runtime | result | median µs | min µs | max µs
|
||||
--------------------------------------------------------------------------------
|
||||
smarm 1-thread | 1000 | 16990 | 16853 | 17540
|
||||
smarm 1-thread | 1000 | 16944 | 16740 | 18603
|
||||
tokio current_thread | 1000 | 937 | 921 | 1056
|
||||
tokio multi-thread | 1000 | 4342 | 4205 | 4549
|
||||
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 | 130032 | 128075 | 153842
|
||||
smarm 1-thread | 10000 | 126396 | 125101 | 131406
|
||||
tokio current_thread | 10000 | 2685 | 2629 | 2841
|
||||
tokio multi-thread | 10000 | 6014 | 4126 | 11484
|
||||
|
||||
================================================================================
|
||||
mpsc_contention: 32 producers × 10000 msgs → 1 consumer
|
||||
================================================================================
|
||||
runtime | result | median µs | min µs | max µs
|
||||
--------------------------------------------------------------------------------
|
||||
smarm 1-thread | 320000 | 9122 | 8987 | 9334
|
||||
smarm 1-thread | 320000 | 9073 | 8956 | 10151
|
||||
tokio current_thread | 320000 | 17259 | 17163 | 17673
|
||||
tokio multi-thread | 320000 | 22771 | 17709 | 24514
|
||||
|
||||
================================================================================
|
||||
many_timers: 10000 actors sleeping 1–10 ms
|
||||
================================================================================
|
||||
runtime | result | median µs | min µs | max µs
|
||||
--------------------------------------------------------------------------------
|
||||
smarm 1-thread | 10000 | 137844 | 134570 | 157034
|
||||
smarm 1-thread | 10000 | 141200 | 137494 | 156214
|
||||
tokio current_thread | 10000 | 14809 | 14024 | 16518
|
||||
tokio multi-thread | 10000 | 15089 | 14704 | 15331
|
||||
|
||||
================================================================================
|
||||
multi_thread_scaling: primes in [2, 400000) across 64 workers
|
||||
================================================================================
|
||||
runtime | result | median µs | min µs | max µs
|
||||
--------------------------------------------------------------------------------
|
||||
smarm 1-thread | 33860 | 30880 | 29931 | 32667
|
||||
tokio multi 1-thread | 33860 | 29862 | 29116 | 31310
|
||||
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 | 90 | 80 | 196
|
||||
smarm 1-thread | 1 | 87 | 79 | 126
|
||||
tokio current_thread | 1 | 25 | 25 | 53
|
||||
tokio multi-thread | 1 | 52 | 47 | 88
|
||||
|
||||
================================================================================
|
||||
yield_in_hot_loop: 2 actors × 500000 yields (single thread)
|
||||
================================================================================
|
||||
runtime | result | median µs | min µs | max µs
|
||||
--------------------------------------------------------------------------------
|
||||
smarm 1-thread | 1000000 | 191187 | 187194 | 198269
|
||||
tokio current_thread | 1000000 | 152531 | 151113 | 154462
|
||||
|
||||
================================================================================
|
||||
uncontended_channel: 1→1, 1000000 msgs (single thread)
|
||||
================================================================================
|
||||
runtime | result | median µs | min µs | max µs
|
||||
--------------------------------------------------------------------------------
|
||||
smarm 1-thread | 1000000 | 27413 | 27312 | 29463
|
||||
tokio current_thread | 1000000 | 53620 | 52594 | 55332
|
||||
|
||||
================================================================================
|
||||
catch_unwind_panics: 10000 tasks, 50% panic
|
||||
================================================================================
|
||||
runtime | result | median µs | min µs | max µs
|
||||
--------------------------------------------------------------------------------
|
||||
smarm 1-thread | 10000 | 144199 | 141893 | 157984
|
||||
smarm 1-thread | 10000 | 144857 | 142722 | 152275
|
||||
tokio current_thread | 10000 | 268006 | 264666 | 274542
|
||||
tokio multi-thread | 10000 | 271827 | 268740 | 290301
|
||||
Reference in New Issue
Block a user