ChatGPT's diagnostic logging revealed the true nature of the problem: TLS SLL head is being corrupted with garbage values from external sources, not a next-pointer offset calculation error. Key Insights: ✅ SuperSlab registration works correctly ❌ TLS head gets overwritten after registration ❌ Corruption occurs between push and pop_enter ❌ Corrupted values are unregistered pointers (memory garbage) Root Cause Candidates (in priority order): A. TLS variable overflow (neighboring variable boundary issue) B. memset/memcpy range error (size calculation wrong) C. TLS initialization duplication (init called twice) Current Defense: - tls_sll_sanitize_head() detects and resets corrupted lists - Prevents propagation of corruption - Cost: 1-5 cycles/pop (negligible) Next ChatGPT Tasks (A/B/C): 1. Audit TLS variable memory layout completely 2. Check all memset/memcpy operating on TLS area 3. Verify TLS initialization only runs once per thread This marks a major breakthrough in understanding the root cause. Expected resolution time: 2-4 hours for complete diagnosis. 🤖 Generated with Claude Code (https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
Docs Overview
このフォルダは hakmem の設計・計測・運用メモを体系化して管理する場所です。
- INDEX.md: 目次(各ドキュメントへのリンク)
- benchmarks/: ベンチマーク手順とスイープ結果の保存先
- specs/: 現在の仕様(SACS‑3/HW/ENV)を集約
- roadmap/: これからの実装計画・優先度・タスク
運用ルール(提案)
- 1つの変更/計測のまとまりにつき1ファイル(or 1フォルダ)
- 再現コマンド・環境変数・ハード構成は必ず記載
- 大きな連続出力はファイルへ保存し、本文からは抜粋/要約を記載