Files
hakmem/docs/analysis/PHASE43_HEADER_WRITE_TAX_REDUCTION_INSTRUCTIONS.md
Moe Charm (CI) 7adbcdfcb6 Phase 54-60: Memory-Lean mode, Balanced mode stabilization, M1 (50%) achievement
## Summary

Completed Phase 54-60 optimization work:

**Phase 54-56: Memory-Lean mode (LEAN+OFF prewarm suppression)**
- Implemented ss_mem_lean_env_box.h with ENV gates
- Balanced mode (LEAN+OFF) promoted as production default
- Result: +1.2% throughput, better stability, zero syscall overhead
- Added to bench_profile.h: MIXED_TINYV3_C7_BALANCED preset

**Phase 57: 60-min soak finalization**
- Balanced mode: 60-min soak, RSS drift 0%, CV 5.38%
- Speed-first mode: 60-min soak, RSS drift 0%, CV 1.58%
- Syscall budget: 1.25e-7/op (800× under target)
- Status: PRODUCTION-READY

**Phase 59: 50% recovery baseline rebase**
- hakmem FAST (Balanced): 59.184M ops/s, CV 1.31%
- mimalloc: 120.466M ops/s, CV 3.50%
- Ratio: 49.13% (M1 ACHIEVED within statistical noise)
- Superior stability: 2.68× better CV than mimalloc

**Phase 60: Alloc pass-down SSOT (NO-GO)**
- Implemented alloc_passdown_ssot_env_box.h
- Modified malloc_tiny_fast.h for SSOT pattern
- Result: -0.46% (NO-GO)
- Key lesson: SSOT not applicable where early-exit already optimized

## Key Metrics

- Performance: 49.13% of mimalloc (M1 effectively achieved)
- Stability: CV 1.31% (superior to mimalloc 3.50%)
- Syscall budget: 1.25e-7/op (excellent)
- RSS: 33MB stable, 0% drift over 60 minutes

## Files Added/Modified

New boxes:
- core/box/ss_mem_lean_env_box.h
- core/box/ss_release_policy_box.{h,c}
- core/box/alloc_passdown_ssot_env_box.h

Scripts:
- scripts/soak_mixed_single_process.sh
- scripts/analyze_epoch_tail_csv.py
- scripts/soak_mixed_rss.sh
- scripts/calculate_percentiles.py
- scripts/analyze_soak.py

Documentation: Phase 40-60 analysis documents

## Design Decisions

1. Profile separation (core/bench_profile.h):
   - MIXED_TINYV3_C7_SAFE: Speed-first (no LEAN)
   - MIXED_TINYV3_C7_BALANCED: Balanced mode (LEAN+OFF)

2. Box Theory compliance:
   - All ENV gates reversible (HAKMEM_SS_MEM_LEAN, HAKMEM_ALLOC_PASSDOWN_SSOT)
   - Single conversion points maintained
   - No physical deletions (compile-out only)

3. Lessons learned:
   - SSOT effective only where redundancy exists (Phase 60 showed limits)
   - Branch prediction extremely effective (~0 cycles for well-predicted branches)
   - Early-exit pattern valuable even when seemingly redundant

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2025-12-17 06:24:01 +09:00

2.7 KiB
Raw Blame History

Phase 43 — Header write tax reductionalloc hot: preserve-class skip

目的

FAST buildmake perf_fast)で、tiny_region_id_write_headeralloc hot実作業を減らして +1% 以上を狙う。

Phase 42 の結論: gate はもう Top 50 圏外。次は「実作業header store」が芯。

背景(観測)

  • tiny_region_id_write_header が runtime profiling で大きいalloc の固定作業)。
  • Tiny の nextptr 仕様では C1C6 は header を保持next_off=1、C0/C7 は header を上書きnext_off=0
    • core/tiny_nextptr.hSSOT
    • core/box/tiny_header_box.htiny_class_preserves_header()

つまり **C1C6 については “free 中に header が壊れない”**前提が成立するので、alloc で毎回 header を書く必要が本来ない。

方針Box Theory

  • Standard/OBSERVE は触らない(安全・互換を維持)。
  • FASTHAKMEM_BENCH_MINIMAL=1の中だけで、alloc 側の header write を減らす。
  • link-out / 物理削除は禁止layout tax の前例がある)。

Step 0: Invariant 確認(必須)

  1. nextptr 仕様確認
  • C0: next_off=0header 上書き)
  • C1C6: next_off=1header 保持)
  • C7: next_off=0デフォルト
  1. 「header 保持クラス」の block が最初に header を持つこと
  • linear carve / refill 経路で、C1C6 には header が書かれていることを確認する。
    • 例: core/tiny_refill_opt.h の carve/popfreenode で tiny_header_write_if_preserved() が走ること

Step 1: 変更FAST 限定)

ターゲット:

  • core/tiny_region_id.htiny_region_id_write_header(...) の hot 経路

変更方針:

  • tiny_class_preserves_header(class_idx)==true のクラスC1C6について、
    • FAST では alloc 時の header store をスキップ
    • user = header_ptr + 1 を返すだけheader は “既に正しい”前提)
  • tiny_class_preserves_header(class_idx)==falseC0/C7だけは 従来どおり header を書く

重要:

  • 既存の Phase 21 “HOTFULL” の hot/cold split を壊さないFAST でも HOTFULL の直線性を維持)。

Step 2: A/BFAST 10-run

baseline:

  • make perf_fastFAST v3

treatment:

  • make perf_fastFAST v4 / Phase 43

判定risk 高めなので閾値を上げる):

  • GO: +1.0% 以上
  • NEUTRAL: ±1.0%
  • NO-GO: -1.0% 以下(即 revert

Step 3: 健康診断(最小)

  • make perf_observe を 1回crash/ASSERT がないこと)

ログ

  • docs/analysis/PHASE43_HEADER_WRITE_TAX_REDUCTION_RESULTS.md を作成し、10-run mean/median と判定を書く。
  • docs/analysis/PERFORMANCE_TARGETS_SCORECARD.md の FAST build 履歴を更新。