ec87025da6
## Phase 17 v2: FORCE_LIBC Gap Validation Fix
**Critical bug fix**: Phase 17 v1 の測定が壊れていた
**Problem**: HAKMEM_FORCE_LIBC_ALLOC=1 が FastLane より後でしか見えず、
same-binary A/B が実質 "hakmem vs hakmem" になっていた（+0.39% 誤測定）
**Fix**: core/box/hak_wrappers.inc.h:171 と :645 に g_force_libc_alloc==1 の
early bypass を追加、__libc_malloc/__libc_free に最初に直行
**Result**: 正しい同一バイナリ A/B 測定
- hakmem (FORCE_LIBC=0): 48.99M ops/s
- libc (FORCE_LIBC=1): 79.72M ops/s (+62.7%)
- system binary: 88.06M ops/s (+10.5% vs libc)
**Gap 分解**:
- Allocator 差: +62.7% (主戦場)
- Layout penalty: +10.5% (副次的)
**Conclusion**: Case A 確定 (allocator dominant, NOT layout)
Phase 17 v1 の Case B 判定は誤り。
Files:
- docs/analysis/PHASE17_FORCE_LIBC_GAP_VALIDATION_1_AB_TEST_RESULTS.md (v2)
- docs/analysis/PHASE17_FORCE_LIBC_GAP_VALIDATION_1_NEXT_INSTRUCTIONS.md (updated)
---
## Phase 19: FastLane Instruction Reduction Analysis
**Goal**: libc との instruction gap (-35% instructions, -56% branches) を削減
**perf stat 分析** (FORCE_LIBC=0 vs 1, 200M ops):
- hakmem: 209.09 instructions/op, 52.33 branches/op
- libc: 135.92 instructions/op, 22.93 branches/op
- Delta: +73.17 instructions/op (+53.8%), +29.40 branches/op (+128.2%)
**Hot path** (perf report):
- front_fastlane_try_free: 23.97% cycles
- malloc wrapper: 23.84% cycles
- free wrapper: 6.82% cycles
- **Wrapper overhead: ~55% of all cycles**
**Reduction candidates**:
- A: Wrapper layer 削除 (-17.5 inst/op, +10-15% 期待)
- B: ENV snapshot 統合 (-10.0 inst/op, +5-8%)
- C: Stats 削除 (-5.0 inst/op, +3-5%)
- D: Header inline (-4.0 inst/op, +2-3%)
- E: Route fast path (-3.5 inst/op, +2-3%)
Files:
- docs/analysis/PHASE19_FASTLANE_INSTRUCTION_REDUCTION_1_DESIGN.md
- docs/analysis/PHASE19_FASTLANE_INSTRUCTION_REDUCTION_2_NEXT_INSTRUCTIONS.md
---
## Phase 19-1b: FastLane Direct — GO (+5.88%)
**Strategy**: Wrapper layer を bypass し、core allocator を直接呼ぶ
- free() → free_tiny_fast() (not free_tiny_fast_hot)
- malloc() → malloc_tiny_fast()
**Phase 19-1 が NO-GO (-3.81%) だった原因**:
1. __builtin_expect(fastlane_direct_enabled(), 0) が逆効果（A/B 不公平）
2. free_tiny_fast_hot() が誤選択（free_tiny_fast() が勝ち筋）
**Phase 19-1b の修正**:
1. __builtin_expect() 削除
2. free_tiny_fast() を直接呼び出し
**Result** (Mixed, 10-run, 20M iters, ws=400):
- Baseline (FASTLANE_DIRECT=0): 49.17M ops/s
- Optimized (FASTLANE_DIRECT=1): 52.06M ops/s
- **Delta: +5.88%** (GO 基準 +5% クリア)
**perf stat** (200M iters):
- Instructions/op: 199.90 → 169.45 (-30.45, -15.23%)
- Branches/op: 51.49 → 41.52 (-9.97, -19.36%)
- Cycles/op: 88.88 → 84.37 (-4.51, -5.07%)
- I-cache miss: 111K → 98K (-11.79%)
**Trade-offs** (acceptable):
- iTLB miss: +41.46% (front-end cost)
- dTLB miss: +29.15% (backend cost)
- Overall gain (+5.88%) outweighs costs
**Implementation**:
1. **ENV gate**: core/box/fastlane_direct_env_box.{h,c}
- HAKMEM_FASTLANE_DIRECT=0/1 (default: 0, opt-in)
- Single _Atomic global (wrapper キャッシュ問題を解決)
2. **Wrapper 修正**: core/box/hak_wrappers.inc.h
- malloc: direct call to malloc_tiny_fast() when FASTLANE_DIRECT=1
- free: direct call to free_tiny_fast() when FASTLANE_DIRECT=1
- Safety: !g_initialized では direct 使わない、fallback 維持
3. **Preset 昇格**: core/bench_profile.h:88
- bench_setenv_default("HAKMEM_FASTLANE_DIRECT", "1")
- Comment: +5.88% proven on Mixed, 10-run
4. **cleanenv 更新**: scripts/run_mixed_10_cleanenv.sh:22
- HAKMEM_FASTLANE_DIRECT=${HAKMEM_FASTLANE_DIRECT:-1}
- Phase 9/10 と同様に昇格
**Verdict**: GO — 本線採用、プリセット昇格完了
**Rollback**: HAKMEM_FASTLANE_DIRECT=0 で既存 FastLane path に戻る
Files:
- core/box/fastlane_direct_env_box.{h,c} (new)
- core/box/hak_wrappers.inc.h (modified)
- core/bench_profile.h (preset promotion)
- scripts/run_mixed_10_cleanenv.sh (ENV default aligned)
- Makefile (new obj)
- docs/analysis/PHASE19_1B_FASTLANE_DIRECT_REVISED_AB_TEST_RESULTS.md
---
## Cumulative Performance
- Baseline (all optimizations OFF): ~40M ops/s (estimated)
- Current (Phase 19-1b): 52.06M ops/s
- **Cumulative gain: ~+30% from baseline**
Remaining gap to libc (79.72M):
- Current: 52.06M ops/s
- Target: 79.72M ops/s
- **Gap: +53.2%** (was +62.7% before Phase 19-1b)
Next: Phase 19-2 (ENV snapshot consolidation, +5-8% expected)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2.7 KiB
2.7 KiB
Phase 19-2: FASTLANE_DIRECT Promotion + Rebaseline (Next Instructions)
0. Status (where we are)
- Phase 19-1b (FASTLANE_DIRECT) is GO: throughput +5.88% with -15.23% instr/op and -19.36% branches/op.
- Safety hardening completed:
!g_initialized→ direct path is skipped (fail-fast, same rule as Front FastLane).- malloc miss no longer calls
malloc_cold()directly; it falls through to the normal wrapper path (preservesg_hakmem_lock_depthinvariants). - ENV cache is a single global
_Atomicsobench_profilerefresh affects wrappers.
1. Promotion policy (Box Theory)
- Keep rollback simple:
HAKMEM_FASTLANE_DIRECT=0→ disable (fallback to Phase 6 FastLane wrapper path).HAKMEM_FASTLANE_DIRECT=1→ enable (directmalloc_tiny_fast()/free_tiny_fast()first).
- Promotion level:
- Preset promotion (recommended): set
HAKMEM_FASTLANE_DIRECT=1inMIXED_TINYV3_C7_SAFEandC6_HEAVY_LEGACY_POOLV1presets. - Keep ENV default = 0 (opt-in) until real-world/LD_PRELOAD validation is done.
- Preset promotion (recommended): set
2. Required verification (same-binary A/B)
2.1 Mixed (10-run, clean env)
Baseline:
HAKMEM_PROFILE=MIXED_TINYV3_C7_SAFE HAKMEM_FASTLANE_DIRECT=0 scripts/run_mixed_10_cleanenv.sh
Optimized:
HAKMEM_PROFILE=MIXED_TINYV3_C7_SAFE HAKMEM_FASTLANE_DIRECT=1 scripts/run_mixed_10_cleanenv.sh
GO/NO-GO:
- GO: mean +1.0% or higher
- NEUTRAL: ±1.0% → keep as preset-only (do not flip global default)
- NO-GO: ≤ -1.0% → revert preset promotion
2.2 C6-heavy (5-run)
HAKMEM_PROFILE=C6_HEAVY_LEGACY_POOLV1 HAKMEM_FASTLANE_DIRECT=0 ./bench_mid_large_mt_hakmem 1 1000000 400 1
HAKMEM_PROFILE=C6_HEAVY_LEGACY_POOLV1 HAKMEM_FASTLANE_DIRECT=1 ./bench_mid_large_mt_hakmem 1 1000000 400 1
3. Perf stat capture (root-cause guardrails)
Run both A/B with:
perf stat -e cycles,instructions,branches,branch-misses,L1-icache-load-misses,iTLB-load-misses,dTLB-load-misses -- \
./bench_random_mixed_hakmem 200000000 400 1
Checklist:
instructions/opandbranches/opmust improve (expected)- iTLB/dTLB misses may worsen; accept only if throughput still improves
4. Next target selection (after promotion)
After Phase 19-2 is stable, re-run perf record on Mixed and choose the next box by self% ≥ 5%:
- If
unified_cache_push/poprises: focus on UnifiedCache data-path (touch fewer cache lines). - If
tiny_header_finalize_allocrises: focus on header finalize path (but treat as high NO-GO risk; prior header work was often NEUTRAL). - If ENV checks reappear in hot path: consider Phase 19-3 (ENV check consolidation), but keep it in a separate research box.