0546454168
ChatGPT's diagnostic changes to address TLS_SLL_HDR_RESET issue. Current status: Partial mitigation, but root cause remains. Changes Applied: 1. SuperSlab Registry Fallback (hakmem_super_registry.h) - Added legacy table probe when hash map lookup misses - Prevents NULL returns for valid SuperSlabs during initialization - Status: ✅ Works but may hide underlying registration issues 2. TLS SLL Push Validation (tls_sll_box.h) - Reject push if SuperSlab lookup returns NULL - Reject push if class_idx mismatch detected - Added [TLS_SLL_PUSH_NO_SS] diagnostic message - Status: ✅ Prevents list corruption (defensive) 3. SuperSlab Allocation Class Fix (superslab_allocate.c) - Pass actual class_idx to sp_internal_allocate_superslab - Prevents dummy class=8 causing OOB access - Status: ✅ Root cause fix for allocation path 4. Debug Output Additions - First 256 push/pop operations traced - First 4 mismatches logged with details - SuperSlab registration state logged - Status: ✅ Diagnostic tool (not a fix) 5. TLS Hint Box Removed - Deleted ss_tls_hint_box.{c,h} (Phase 1 optimization) - Simplified to focus on stability first - Status: ⏳ Can be re-added after root cause fixed Current Problem (REMAINS UNSOLVED): - [TLS_SLL_HDR_RESET] still occurs after ~60 seconds of sh8bench - Pointer is 16 bytes offset from expected (class 1 → class 2 boundary) - hak_super_lookup returns NULL for that pointer - Suggests: Use-After-Free, Double-Free, or pointer arithmetic error Root Cause Analysis: - Pattern: Pointer offset by +16 (one class 1 stride) - Timing: Cumulative problem (appears after 60s, not immediately) - Location: Header corruption detected during TLS SLL pop Remaining Issues: ⚠️ Registry fallback is defensive (may hide registration bugs) ⚠️ Push validation prevents symptoms but not root cause ⚠️ 16-byte pointer offset source unidentified Next Steps for Investigation: 1. Full pointer arithmetic audit (Magazine ⇔ TLS SLL paths) 2. Enhanced logging at HDR_RESET point: - Expected vs actual pointer value - Pointer provenance (where it came from) - Allocation trace for that block 3. Verify Headerless flag is OFF throughout build 4. Check for double-offset application in conversions Technical Assessment: - 60% root cause fixes (allocation class, validation) - 40% defensive mitigation (registry fallback, push rejection) Performance Impact: - Registry fallback: +10-30 cycles on cold path (negligible) - Push validation: +5-10 cycles per push (acceptable) - Overall: < 2% performance impact estimated Related Issues: - Phase 1 TLS Hint Box removed temporarily - Phase 2 Headerless blocked until stability achieved 🤖 Generated with Claude Code (https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
1.4 KiB
1.4 KiB
ACE-Alloc Paper Notes (Scratchpad)
このファイルは、ACE / 学習機能まわりの実験メモ・アイデア・ストーリー断片を雑に書き溜めるためのスクラッチパッドです。
後で docs/paper/ACE-Alloc/main.md にまとめ直す前提の「素材置き場」として使います。
アイデアメモ（例）
-
Tiny Headerless + Superslab + ACE の組み合わせで:
- Headerless: free パスでの class 決定を Superslab/region に移し、per-object header を除去。
- ACE Controller: Mid/Large の TLS CAP / drain をオフパスで学習。
- CAP Learner: Mid/Large の CAP / W_MAX をヒット率ベースで調整。
- → 「ヘッダレス＋学習」で、密度と性能を両立できるか？
-
学習の「層ごとの役割分担」:
- L0 Tiny: 原則固定（学習対象外）。ただし Observer だけ Tiny を見る。
- L1 ACE: キャッシュ構成（CAP / drain / bundle）を学習。
- L2 ELO+Evolution: しきい値・戦略の切り替えを学習。
- → Box Theory 的には、学習そのものも「上層の箱」として Tiny/SuperSlab から分離されている。
実験ネタ候補
- ACE ON/OFF が Tiny Headerless の性能・安定性に与える影響。
- HAKMEM_MODE=balanced vs learning vs research での学習挙動の違い。
- LD_PRELOAD モードで学習機能をどこまで有効にできるか（安全性とのトレードオフ）。