Files
hakmem/core/bench_profile.h
Moe Charm (CI) dcc1d42e7f Phase 6-2: Promote Front FastLane Free DeDup (default ON)
Results:
- A/B test: +5.18% on Mixed (10-run, clean env)
- Baseline: 46.68M ops/s
- Optimized: 49.10M ops/s
- Improvement: +2.42M ops/s (+5.18%)

Strategy:
- Eliminate duplicate header validation in front_fastlane_try_free()
- Direct call to free_tiny_fast() when dedup enabled
- Single validation path (no redundant checks)

Success factors:
1. Complete duplicate elimination (free path optimization)
2. Free path importance (50% of Mixed workload)
3. Improved execution stability (CV: 1.00% → 0.58%)

Phase 6 cumulative:
- Phase 6-1 FastLane: +11.13%
- Phase 6-2 Free DeDup: +5.18%
- Total: ~+16-17% from baseline (multiplicative effect)

Promotion:
- Default: HAKMEM_FRONT_FASTLANE_FREE_DEDUP=1 (opt-out)
- Added to MIXED_TINYV3_C7_SAFE preset
- Added to C6_HEAVY_LEGACY_POOLV1 preset
- Rollback: HAKMEM_FRONT_FASTLANE_FREE_DEDUP=0

Files modified:
- core/box/front_fastlane_env_box.h: default 0 → 1
- core/bench_profile.h: added to presets
- CURRENT_TASK.md: Phase 6-2 GO result

Health check: PASSED (all profiles)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2025-12-14 17:38:21 +09:00

182 lines
9.6 KiB
C
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#pragma once
#include <dlfcn.h>
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include <unistd.h>
#ifdef USE_HAKMEM
#include "box/wrapper_env_box.h" // wrapper_env_refresh_from_env (Phase 2 B4)
#include "box/tiny_static_route_box.h" // tiny_static_route_refresh_from_env (Phase 3 C3)
#include "box/hakmem_env_snapshot_box.h" // hakmem_env_snapshot_refresh_from_env (Phase 4 E1)
#endif
// env が未設定のときだけ既定値を入れる
static inline void bench_setenv_default(const char* key, const char* val) {
if (getenv(key) != NULL) return;
static void* (*real_malloc)(size_t) = NULL;
static int (*real_putenv)(char*) = NULL;
if (!real_malloc) {
real_malloc = (void* (*)(size_t))dlsym(RTLD_NEXT, "malloc");
if (!real_malloc) real_malloc = malloc;
}
if (!real_putenv) {
real_putenv = (int (*)(char*))dlsym(RTLD_NEXT, "putenv");
if (!real_putenv) real_putenv = putenv;
}
size_t klen = strlen(key);
size_t vlen = strlen(val);
char* buf = (char*)real_malloc(klen + vlen + 2);
if (!buf) return;
memcpy(buf, key, klen);
buf[klen] = '=';
memcpy(buf + klen + 1, val, vlen);
buf[klen + 1 + vlen] = '\0';
{
char msg[256];
int n = snprintf(msg, sizeof(msg), "[bench_profile] set %s=%s\n", key, val);
if (n > 0) {
if (n > (int)sizeof(msg)) n = (int)sizeof(msg);
ssize_t w = write(2, msg, (size_t)n);
(void)w;
}
}
real_putenv(buf); // takes ownership; do not free
}
// ベンチ専用: HAKMEM_PROFILE に応じて ENV をプリセットする
static inline void bench_apply_profile(void) {
const char* p = getenv("HAKMEM_PROFILE");
if (!p || !*p) return;
if (strcmp(p, "MIXED_TINYV3_C7_SAFE") == 0) {
bench_setenv_default("HAKMEM_TINY_HEAP_PROFILE", "C7_SAFE");
bench_setenv_default("HAKMEM_TINY_C7_HOT", "1");
bench_setenv_default("HAKMEM_TINY_HOTHEAP_V2", "0");
bench_setenv_default("HAKMEM_SMALL_HEAP_V3_ENABLED", "1");
bench_setenv_default("HAKMEM_SMALL_HEAP_V3_CLASSES", "0x80");
bench_setenv_default("HAKMEM_SMALL_HEAP_V4_ENABLED", "0");
bench_setenv_default("HAKMEM_SMALL_HEAP_V4_CLASSES", "0x0");
bench_setenv_default("HAKMEM_TINY_PTR_FAST_CLASSIFY_V4_ENABLED", "0");
bench_setenv_default("HAKMEM_SMALL_SEGMENT_V4_ENABLED", "0");
bench_setenv_default("HAKMEM_POOL_V2_ENABLED", "0");
bench_setenv_default("HAKMEM_TINY_FRONT_V3_ENABLED", "1");
bench_setenv_default("HAKMEM_TINY_FRONT_V3_LUT_ENABLED", "1");
bench_setenv_default("HAKMEM_TINY_PTR_FAST_CLASSIFY_ENABLED", "1");
// Phase FREE-TINY-FAST-DUALHOT-1: C0-C3 direct fast free (skip policy snapshot)
bench_setenv_default("HAKMEM_FREE_TINY_FAST_HOTCOLD", "1");
// Phase 2 B4: Wrapper hot/cold split (malloc/free wrapper shape)
bench_setenv_default("HAKMEM_WRAP_SHAPE", "1");
// Phase 4 E1: ENV Snapshot Consolidation (+3.92% proven on Mixed)
bench_setenv_default("HAKMEM_ENV_SNAPSHOT", "1");
// Phase 5 E4-1: Free wrapper ENV snapshot (+3.51% proven on Mixed, 10-run)
bench_setenv_default("HAKMEM_FREE_WRAPPER_ENV_SNAPSHOT", "1");
// Phase 5 E4-2: Malloc wrapper ENV snapshot (+21.83% proven on Mixed, 10-run)
bench_setenv_default("HAKMEM_MALLOC_WRAPPER_ENV_SNAPSHOT", "1");
// Phase 5 E5-1: Free Tiny Direct Path (+3.35% proven on Mixed, 10-run)
bench_setenv_default("HAKMEM_FREE_TINY_DIRECT", "1");
// Phase 6-1: Front FastLane (Layer Collapse) (+11.13% proven on Mixed, 10-run)
bench_setenv_default("HAKMEM_FRONT_FASTLANE", "1");
// Phase 6-2: Front FastLane Free DeDup (+5.18% proven on Mixed, 10-run)
bench_setenv_default("HAKMEM_FRONT_FASTLANE_FREE_DEDUP", "1");
// Phase 4-4: C6 ULTRA free+alloc 統合を有効化 (default OFF, manual opt-in)
bench_setenv_default("HAKMEM_TINY_C6_ULTRA_FREE_ENABLED", "0");
// Phase MID-V3: Mid/Pool HotBox v3
// Mixed (161024B) では MID_V3(C6) が大きく遅くなるため、デフォルト OFF に固定。
// C6-heavy プロファイル側でのみ ON を推奨するC6-heavy のみ最適化対象)。
bench_setenv_default("HAKMEM_MID_V3_ENABLED", "0");
bench_setenv_default("HAKMEM_MID_V3_CLASSES", "0x0");
// Phase 2 B3: Routing branch shape optimization (LIKELY on LEGACY, cold helper for rare routes)
bench_setenv_default("HAKMEM_TINY_ALLOC_ROUTE_SHAPE", "1");
// Phase 3 C3: Static routing (policy_snapshot bypass, +2.2% proven)
bench_setenv_default("HAKMEM_TINY_STATIC_ROUTE", "1");
// Phase 3 D1: Free route cache (TLS cache for free path routing, +2.19% proven)
bench_setenv_default("HAKMEM_FREE_STATIC_ROUTE", "1");
} else if (strcmp(p, "C6_HEAVY_LEGACY_POOLV1") == 0) {
bench_setenv_default("HAKMEM_TINY_HEAP_PROFILE", "C7_SAFE");
bench_setenv_default("HAKMEM_TINY_C6_HOT", "0");
bench_setenv_default("HAKMEM_TINY_HOTHEAP_V2", "0");
bench_setenv_default("HAKMEM_SMALL_HEAP_V3_ENABLED", "1");
bench_setenv_default("HAKMEM_SMALL_HEAP_V3_CLASSES", "0x80");
bench_setenv_default("HAKMEM_POOL_V2_ENABLED", "0");
bench_setenv_default("HAKMEM_POOL_V1_FLATTEN_ENABLED", "0");
bench_setenv_default("HAKMEM_MID_DESC_CACHE_ENABLED", "1");
// Phase 4-4: C6 ULTRA free+alloc 統合を有効化 (default OFF, manual opt-in)
bench_setenv_default("HAKMEM_TINY_C6_ULTRA_FREE_ENABLED", "0");
// Phase MID-V3: Mid/Pool HotBox v3 (257-768B, C6 only)
bench_setenv_default("HAKMEM_MID_V3_ENABLED", "1");
bench_setenv_default("HAKMEM_MID_V3_CLASSES", "0x40");
// Phase 6-1: Front FastLane (Layer Collapse) (+11.13% proven on Mixed, 10-run)
bench_setenv_default("HAKMEM_FRONT_FASTLANE", "1");
// Phase 6-2: Front FastLane Free DeDup (+5.18% proven on Mixed, 10-run)
bench_setenv_default("HAKMEM_FRONT_FASTLANE_FREE_DEDUP", "1");
// Phase 2 B3: Routing branch shape optimization (LIKELY on LEGACY, cold helper for rare routes)
bench_setenv_default("HAKMEM_TINY_ALLOC_ROUTE_SHAPE", "1");
} else if (strcmp(p, "C6_V7_STUB") == 0) {
// Phase v7-1: C6-only v7 stub 実験用MID v3 fallback
bench_setenv_default("HAKMEM_TINY_HEAP_PROFILE", "C7_SAFE");
bench_setenv_default("HAKMEM_TINY_C6_HOT", "0");
bench_setenv_default("HAKMEM_TINY_HOTHEAP_V2", "0");
bench_setenv_default("HAKMEM_SMALL_HEAP_V3_ENABLED", "1");
bench_setenv_default("HAKMEM_SMALL_HEAP_V3_CLASSES", "0x80");
bench_setenv_default("HAKMEM_POOL_V2_ENABLED", "0");
bench_setenv_default("HAKMEM_MID_V3_ENABLED", "1");
bench_setenv_default("HAKMEM_MID_V3_CLASSES", "0x40");
// v7 stub ON (C6-only)
bench_setenv_default("HAKMEM_SMALL_HEAP_V7_ENABLED", "1");
bench_setenv_default("HAKMEM_SMALL_HEAP_V7_CLASSES", "0x40");
} else if (strcmp(p, "C6_HEAVY_LEGACY_POOLV1_FLATTEN") == 0) {
// LEGACY mid/smallmid ベンチ専用C7_SAFE では使用しない)
bench_setenv_default("HAKMEM_TINY_HEAP_PROFILE", "LEGACY");
bench_setenv_default("HAKMEM_TINY_C6_HOT", "0");
bench_setenv_default("HAKMEM_TINY_HOTHEAP_V2", "0");
bench_setenv_default("HAKMEM_SMALL_HEAP_V3_ENABLED", "1");
bench_setenv_default("HAKMEM_SMALL_HEAP_V3_CLASSES", "0x80");
bench_setenv_default("HAKMEM_POOL_V2_ENABLED", "0");
bench_setenv_default("HAKMEM_POOL_V1_FLATTEN_ENABLED", "1");
bench_setenv_default("HAKMEM_POOL_V1_FLATTEN_STATS", "1");
bench_setenv_default("HAKMEM_POOL_ZERO_MODE", "header");
} else if (strcmp(p, "DEBUG_TINY_FRONT_PERF") == 0) {
bench_setenv_default("HAKMEM_TINY_HEAP_PROFILE", "C7_SAFE");
bench_setenv_default("HAKMEM_TINY_C7_HOT", "1");
bench_setenv_default("HAKMEM_TINY_HOTHEAP_V2", "0");
bench_setenv_default("HAKMEM_SMALL_HEAP_V3_ENABLED", "1");
bench_setenv_default("HAKMEM_SMALL_HEAP_V3_CLASSES", "0x80");
bench_setenv_default("HAKMEM_POOL_V2_ENABLED", "0");
bench_setenv_default("HAKMEM_TINY_FRONT_V3_ENABLED", "1");
bench_setenv_default("HAKMEM_TINY_FRONT_V3_LUT_ENABLED", "1");
bench_setenv_default("HAKMEM_TINY_PTR_FAST_CLASSIFY_ENABLED", "1");
} else if (strcmp(p, "C6_SMALL_HEAP_V3_EXPERIMENT") == 0) {
// C6 を SmallObject v3 に載せる研究用(標準では使用しない)
bench_setenv_default("HAKMEM_TINY_HEAP_PROFILE", "C7_SAFE");
bench_setenv_default("HAKMEM_TINY_C6_HOT", "1");
bench_setenv_default("HAKMEM_TINY_HOTHEAP_V2", "0");
bench_setenv_default("HAKMEM_SMALL_HEAP_V3_ENABLED", "1");
bench_setenv_default("HAKMEM_SMALL_HEAP_V3_CLASSES", "0x40"); // C6 only
bench_setenv_default("HAKMEM_SMALL_HEAP_V4_ENABLED", "0");
bench_setenv_default("HAKMEM_SMALL_HEAP_V4_CLASSES", "0x0");
bench_setenv_default("HAKMEM_POOL_V2_ENABLED", "0");
} else if (strcmp(p, "C6_SMALL_HEAP_V4_EXPERIMENT") == 0) {
// C6 を SmallObject v4 に載せる研究用(標準では使用しない)
bench_setenv_default("HAKMEM_TINY_HEAP_PROFILE", "C7_SAFE");
bench_setenv_default("HAKMEM_TINY_C6_HOT", "1");
bench_setenv_default("HAKMEM_TINY_HOTHEAP_V2", "0");
bench_setenv_default("HAKMEM_SMALL_HEAP_V3_ENABLED", "0");
bench_setenv_default("HAKMEM_SMALL_HEAP_V3_CLASSES", "0x0");
bench_setenv_default("HAKMEM_SMALL_HEAP_V4_ENABLED", "1");
bench_setenv_default("HAKMEM_SMALL_HEAP_V4_CLASSES", "0x40"); // C6 only
bench_setenv_default("HAKMEM_POOL_V2_ENABLED", "0");
}
#ifdef USE_HAKMEM
// Phase 3 C3 Step 0: Ensure policy snapshot reflects final ENV after putenv defaults.
small_policy_v7_bump_version();
// Phase 2 B4: Sync wrapper ENV cache after bench_profile putenv defaults.
wrapper_env_refresh_from_env();
// Phase 3 C3: Sync static route cache after bench_profile putenv defaults.
tiny_static_route_refresh_from_env();
// Phase 4 E1: Sync ENV snapshot cache after bench_profile putenv defaults.
hakmem_env_snapshot_refresh_from_env();
#endif
}