tomoaki/hakmem
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
b7085c47e1c91d7ec80eda97f4db112cb81c3ee4
hakmem/core/bench_profile.h
Moe Charm (CI) 8052e8b320 Phase 24-26: Hot path atomic telemetry prune (+2.00% cumulative) 
Summary:
- Phase 24 (alloc stats): +0.93% GO
- Phase 25 (free stats): +1.07% GO
- Phase 26 (diagnostics): -0.33% NEUTRAL (code cleanliness)
- Total: 11 atomics compiled-out, +2.00% improvement

Phase 24: OBSERVE tax prune (tiny_class_stats_box.h)
- Added HAKMEM_TINY_CLASS_STATS_COMPILED (default: 0)
- Wrapped 5 stats functions: uc_miss, warm_hit, shared_lock, tls_carve_*
- Result: +0.93% (baseline 56.675M vs compiled-in 56.151M ops/s)

Phase 25: Tiny free stats prune (tiny_superslab_free.inc.h)
- Added HAKMEM_TINY_FREE_STATS_COMPILED (default: 0)
- Wrapped g_free_ss_enter atomic in free hot path
- Result: +1.07% (baseline 57.017M vs compiled-in 56.415M ops/s)

Phase 26: Hot path diagnostic atomics prune
- Added 5 compile gates for low-frequency error counters:
  - HAKMEM_TINY_C7_FREE_COUNT_COMPILED
  - HAKMEM_TINY_HDR_MISMATCH_LOG_COMPILED
  - HAKMEM_TINY_HDR_META_MISMATCH_COMPILED
  - HAKMEM_TINY_METRIC_BAD_CLASS_COMPILED
  - HAKMEM_TINY_HDR_META_FAST_COMPILED
- Result: -0.33% NEUTRAL (within noise, kept for cleanliness)

Alignment with mimalloc principles:
- "No atomics on hot path" - telemetry moved to compile-time opt-in
- Fixed per-op tax elimination
- Production builds: maximum performance (atomics compiled-out)
- Research builds: full diagnostics (COMPILED=1)

Generated with Claude Code
https://claude.com/claude-code

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2025-12-16 05:35:11 +09:00

215 lines
12 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)
#include "box/tiny_free_route_cache_env_box.h" // tiny_free_static_route_refresh_from_env (Phase 8)
#include "box/tiny_c7_preserve_header_env_box.h" // tiny_c7_preserve_header_env_refresh_from_env (Phase 13 v1)
#include "box/tiny_tcache_env_box.h" // tiny_tcache_env_refresh_from_env (Phase 14 v1)
#include "box/tiny_unified_lifo_env_box.h" // tiny_unified_lifo_env_refresh_from_env (Phase 15 v1)
#include "box/front_fastlane_alloc_legacy_direct_env_box.h" // front_fastlane_alloc_legacy_direct_env_refresh_from_env (Phase 16 v1)
#include "box/fastlane_direct_env_box.h" // fastlane_direct_env_refresh_from_env (Phase 19-1)
#include "box/tiny_header_hotfull_env_box.h" // tiny_header_hotfull_env_refresh_from_env (Phase 21)
#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 21: Tiny Header HotFull (alloc header hot/cold split; opt-out with 0)
bench_setenv_default("HAKMEM_TINY_HEADER_HOTFULL", "1");
// Phase 19-1b: FastLane Direct (wrapper layer bypass, +5.88% proven on Mixed, 10-run)
bench_setenv_default("HAKMEM_FASTLANE_DIRECT", "1");
// Phase 9: FREE-TINY-FAST MONO DUALHOT (+2.72% proven on Mixed, 10-run)
bench_setenv_default("HAKMEM_FREE_TINY_FAST_MONO_DUALHOT", "1");
// Phase 10: FREE-TINY-FAST MONO LEGACY DIRECT (+1.89% proven on Mixed, 10-run)
bench_setenv_default("HAKMEM_FREE_TINY_FAST_MONO_LEGACY_DIRECT", "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 (16–1024B) 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 21: Tiny Header HotFull (alloc header hot/cold split; opt-out with 0)
bench_setenv_default("HAKMEM_TINY_HEADER_HOTFULL", "1");
// Phase 19-1b: FastLane Direct (wrapper layer bypass)
bench_setenv_default("HAKMEM_FASTLANE_DIRECT", "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();
// Phase 8: Sync free static route ENV cache after bench_profile putenv defaults.
tiny_free_static_route_refresh_from_env();
// Phase 13 v1: Sync C7 preserve header ENV cache after bench_profile putenv defaults.
tiny_c7_preserve_header_env_refresh_from_env();
// Phase 14 v1: Sync tcache ENV cache after bench_profile putenv defaults.
tiny_tcache_env_refresh_from_env();
// Phase 15 v1: Sync LIFO ENV cache after bench_profile putenv defaults.
tiny_unified_lifo_env_refresh_from_env();
// Phase 16 v1: Sync LEGACY direct ENV cache after bench_profile putenv defaults.
front_fastlane_alloc_legacy_direct_env_refresh_from_env();
// Phase 19-1: Sync FastLane Direct ENV cache after bench_profile putenv defaults.
fastlane_direct_env_refresh_from_env();
// Phase 21: Sync Tiny Header HotFull ENV cache after bench_profile putenv defaults.
tiny_header_hotfull_env_refresh_from_env();
#endif
}
Reference in New Issue View Git Blame Copy Permalink