Files
hakmem/benchmarks
Moe Charm (CI) 1010a961fb Tiny: fix header/stride mismatch and harden refill paths
- Root cause: header-based class indexing (HEADER_CLASSIDX=1) wrote a 1-byte
  header during allocation, but linear carve/refill and initial slab capacity
  still used bare class block sizes. This mismatch could overrun slab usable
  space and corrupt freelists, causing reproducible SEGV at ~100k iters.

Changes
- Superslab: compute capacity with effective stride (block_size + header for
  classes 0..6; class7 remains headerless) in superslab_init_slab(). Add a
  debug-only bound check in superslab_alloc_from_slab() to fail fast if carve
  would exceed usable bytes.
- Refill (non-P0 and P0): use header-aware stride for all linear carving and
  TLS window bump operations. Ensure alignment/validation in tiny_refill_opt.h
  also uses stride, not raw class size.
- Drain: keep existing defense-in-depth for remote sentinel and sanitize nodes
  before splicing into freelist (already present).

Notes
- This unifies the memory layout across alloc/linear-carve/refill with a single
  stride definition and keeps class7 (1024B) headerless as designed.
- Debug builds add fail-fast checks; release builds remain lean.

Next
- Re-run Tiny benches (256/1024B) in debug to confirm stability, then in
  release. If any remaining crash persists, bisect with HAKMEM_TINY_P0_BATCH_REFILL=0
  to isolate P0 batch carve, and continue reducing branch-miss as planned.
2025-11-09 18:55:50 +09:00
..

Benchmarks Catalog

このディレクトリのベンチを用途別に整理しました。各ベンチは System/mimalloc/HAKMEM直リンク or LD_PRELOADの三者比較、もしくは HAKMEM の A/B環境変数を想定しています。

ベンチ種類(バイナリ)

  • Tiny Hot864B、ホットパス/LIFO

    • benchmarks/src/tiny/bench_tiny_hot.c
    • バイナリ: bench_tiny_hot_system, bench_tiny_hot_hakmem, bench_tiny_hot_mi
    • 例: ./bench_tiny_hot_hakmem 64 100 60000
  • Random Mixed161024B、単体

    • バイナリ: bench_random_mixed_system, bench_random_mixed_hakmem
    • 例: ./bench_random_mixed_hakmem 400000 8192 123
  • Mid/Large MT832KiB、マルチスレッド

    • バイナリ: bench_mid_large_mt_system, bench_mid_large_mt_hakmem
    • 例: ./bench_mid_large_mt_hakmem 4 40000 2048 42
  • VM Mixed512KB<2MB、L2.5/L2 の再利用確認)

    • バイナリ: bench_vm_mixed_system, bench_vm_mixed_hakmem
    • 例: HAKMEM_BIGCACHE_L25=1 HAKMEM_WRAP_TINY=1 ./bench_vm_mixed_hakmem 20000 256 4242
  • Larson8128B、mimalloc-bench 派生)

    • バイナリ: larson_system, larson_mi, larson_hakmem
    • 例: ./larson_hakmem 2 8 128 1024 1 12345 4
  • Redis-like161024B、アプリ風

    • バイナリ: benchmarks/redis/workload_bench_system
    • 直リンク: System のみ。mimalloc/HAKMEM は LD_PRELOAD で比較HAKMEM は安定化中)。

マトリクス実行CSV保存

  • Random Mixed直リンク

    • benchmarks/scripts/run_random_mixed_matrix.sh [cycles] [ws] [reps]
    • 出力: bench_results/auto/random_mixed_<ts>/results.csv
  • Mid/Large MT直リンク

    • benchmarks/scripts/run_mid_large_mt_matrix.sh [threads_csv] [cycles] [ws] [reps]
    • 出力: bench_results/auto/mid_large_mt_<ts>/results.csv
  • VM MixedL2.5/L2、HAKMEMのL25 A/B

    • benchmarks/scripts/run_vm_mixed_matrix.sh [cycles] [ws] [reps]
    • 出力: bench_results/auto/vm_mixed_<ts>/results.csv
  • Larson補助

    • scripts/run_larson.sh(直リンク triadscripts/run_larson_claude.sh(環境プリセット付き)

代表的な環境変数

  • HAKMEM_WRAP_TINY=1 → HAKMEM/Tiny を有効化(直リンクベンチ)
  • HAKMEM_TINY_READY=0/1 → Ready Listrefill最適化
  • HAKMEM_TINY_SS_ADOPT=0/1 → publish→adopt 経路
  • HAKMEM_BIGCACHE_L25=0/1 → L2.5512KB<2MBを BigCache にも載せるA/B

参考出力(短時間ランの目安)

  • 直近の短ランのスナップショットは benchmarks/RESULTS_SNAPSHOT.md を参照してください。正式な比較は各マトリクススクリプトで reps=5/10・長時間ラン例: 10sを推奨します。