=== 実装内容 === 1. v3 backend 詳細計測 - ENV: HAKMEM_SO_V3_STATS で alloc/free パス内訳計測 - 追加 stats: alloc_current_hit, alloc_partial_hit, free_current, free_partial, free_retire - so_alloc_fast / so_free_fast に埋め込み - デストラクタで [ALLOC_DETAIL] / [FREE_DETAIL] 出力 2. v3 backend ボトルネック分析完了 - C7-only: alloc_current_hit=99.99%, alloc_refill=0.9%, free_retire=0.1%, page_of_fail=0 - Mixed: alloc_current_hit=100%, alloc_refill=0.85%, free_retire=0.07%, page_of_fail=0 - 結論: v3 ロジック部分(ページ選択・retire)は完全最適化済み - 残り 5% overhead は内部コスト(header write, memcpy, 分岐) 3. Tiny/ULTRA 層「完成世代」宣言 - 総括ドキュメント作成: docs/analysis/PERF_EXEC_SUMMARY_ULTRA_PHASE_20251211.md - CURRENT_TASK.md に Phase ULTRA 総括セクション追加 - AGENTS.md に Tiny/ULTRA 完成世代宣言追加 - 最終成果: Mixed 16–1024B = 43.9M ops/s (baseline 30.6M → +43.5%) === ボトルネック地図 === | 層 | 関数 | overhead | |-----|------|----------| | Front | malloc/free dispatcher | ~40–45% | | ULTRA | C4–C7 alloc/free/refill | ~12% | | v3 backend | so_alloc/so_free | ~5% | | mid/pool | hak_super_lookup | 3–5% | === フェーズ履歴(Phase ULTRA cycle) === - Phase PERF-ULTRA-FREE-OPT-1: C4–C7 ULTRA統合 → +9.3% - Phase REFACTOR: Code quality (60行削減) - Phase PERF-ULTRA-REFILL-OPT-1a/1b: C7 ULTRA refill最適化 → +11.1% - Phase SO-BACKEND-OPT-1: v3 backend分解 → 設計限界確認 === 次フェーズ(独立ライン) === 1. Phase SO-BACKEND-OPT-2: v3 header write削減 (1-2%) 2. Headerless/v6系: out-of-band header (1-2%) 3. mid/pool v3新設計: C6-heavy 10M → 20–25M 本フェーズでTiny/ULTRA層は「完成世代」として基盤固定。 今後の大きい変更はHeaderless/mid系の独立ラインで検討。 🤖 Generated with Claude Code Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
90 lines
3.0 KiB
C
90 lines
3.0 KiB
C
// smallobject_hotbox_v3_box.h - SmallObject HotHeap v3 (C7-first skeleton)
|
||
//
|
||
// Phase A/B: 型と TLS / stats を用意し、front が呼べる枠を置く。
|
||
// まだ中身は v1 fallback(so_alloc は NULL を返す)。
|
||
#pragma once
|
||
|
||
#include <stdint.h>
|
||
#include <stddef.h>
|
||
#include <stdatomic.h>
|
||
#include "tiny_geometry_box.h"
|
||
#include "smallobject_hotbox_v3_env_box.h"
|
||
#include "tiny_region_id.h"
|
||
|
||
#ifndef SMALLOBJECT_NUM_CLASSES
|
||
#define SMALLOBJECT_NUM_CLASSES TINY_NUM_CLASSES
|
||
#endif
|
||
|
||
struct tiny_heap_page_t;
|
||
struct TinySlabMeta;
|
||
struct SuperSlab;
|
||
|
||
typedef struct so_page_v3 {
|
||
void* freelist;
|
||
uint32_t used;
|
||
uint32_t capacity;
|
||
uint32_t block_size;
|
||
uint32_t class_idx;
|
||
uint32_t flags;
|
||
void* base; // carve 後のユーザ領域先頭
|
||
void* slab_base; // 64KiB slab 基底(page_of 用ヘッダを書き込む)
|
||
struct TinySlabMeta* meta;
|
||
struct SuperSlab* ss;
|
||
uint16_t slab_idx;
|
||
struct tiny_heap_page_t* lease_page;
|
||
void* slab_ref; // kept as a generic token; currently same as lease_page for v1
|
||
struct so_page_v3* next;
|
||
} so_page_v3;
|
||
|
||
typedef struct so_class_v3 {
|
||
so_page_v3* current;
|
||
so_page_v3* partial;
|
||
uint16_t max_partial_pages;
|
||
uint16_t partial_count;
|
||
uint32_t block_size;
|
||
} so_class_v3;
|
||
|
||
typedef struct so_ctx_v3 {
|
||
so_class_v3 cls[SMALLOBJECT_NUM_CLASSES];
|
||
} so_ctx_v3;
|
||
|
||
typedef struct so_stats_class_v3 {
|
||
_Atomic uint64_t route_hits;
|
||
_Atomic uint64_t alloc_calls;
|
||
_Atomic uint64_t alloc_refill;
|
||
_Atomic uint64_t alloc_fallback_v1;
|
||
_Atomic uint64_t alloc_current_hit; // fast path: current から pop
|
||
_Atomic uint64_t alloc_partial_hit; // fast path: partial から pop
|
||
_Atomic uint64_t free_calls;
|
||
_Atomic uint64_t free_fallback_v1;
|
||
_Atomic uint64_t free_current; // fast path: current に push
|
||
_Atomic uint64_t free_partial; // fast path: partial に push
|
||
_Atomic uint64_t free_retire; // slow path: retire
|
||
_Atomic uint64_t page_of_fail;
|
||
} so_stats_class_v3;
|
||
|
||
// Stats helpers (defined in core/smallobject_hotbox_v3.c)
|
||
int so_v3_stats_enabled(void);
|
||
void so_v3_record_route_hit(uint8_t ci);
|
||
void so_v3_record_alloc_call(uint8_t ci);
|
||
void so_v3_record_alloc_refill(uint8_t ci);
|
||
void so_v3_record_alloc_fallback(uint8_t ci);
|
||
void so_v3_record_alloc_current_hit(uint8_t ci);
|
||
void so_v3_record_alloc_partial_hit(uint8_t ci);
|
||
void so_v3_record_free_call(uint8_t ci);
|
||
void so_v3_record_free_fallback(uint8_t ci);
|
||
void so_v3_record_free_current(uint8_t ci);
|
||
void so_v3_record_free_partial(uint8_t ci);
|
||
void so_v3_record_free_retire(uint8_t ci);
|
||
void so_v3_record_page_of_fail(uint8_t ci);
|
||
|
||
// TLS accessor (core/smallobject_hotbox_v3.c)
|
||
so_ctx_v3* so_tls_get(void);
|
||
|
||
// Hot path API (Phase B: stub → always fallback to v1)
|
||
void* so_alloc(uint32_t class_idx);
|
||
void so_free(uint32_t class_idx, void* ptr);
|
||
|
||
// C7-only pointer membership check (read-only, no state change)
|
||
int smallobject_hotbox_v3_can_own_c7(void* ptr);
|