## Phase POLICY-FAST-PATH-V2 (FROZEN) - Implementation complete: free_policy_fast_v2_box.h + malloc_tiny_fast.h integration - A/B Results: - Mixed (ws=400): -1.6% regression ❌ (branch cost > skip benefit) - C6-heavy (ws=200): +5.4% improvement ✅ - Decision: Default OFF, FROZEN (ws<300 / C6-heavy research only) - Learning: Large WS causes branch misprediction to dominate ## Phase 3-GRADUATE + ENV probe fix - 64-probe retry for getenv() stability during bench_profile putenv() - C6 ULTRA intrusive freelist: FROZEN (research box) ## Phase MID-V35-HOTPATH-OPT-1-DESIGN - Design doc for next optimization target - Target: MID v3.5 alloc/free hot path (C5-C6) - Boxes: Stats Gate, TLS Layout, Boundary Check elimination - Expected: +3-9% on Mixed mainline Files: - core/box/free_policy_fast_v2_box.h (new) - core/box/free_path_stats_box.h/c (policy_fast_v2_skip counter) - core/front/malloc_tiny_fast.h (fast-path integration) - docs/analysis/MID_V35_HOTPATH_OPT_1_DESIGN.md (new) - docs/analysis/PHASE_3_GRADUATE_*.md (new) - CURRENT_TASK.md (phase status update) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
69 lines
2.3 KiB
C
69 lines
2.3 KiB
C
#ifndef HAKMEM_FREE_PATH_STATS_BOX_H
|
|
#define HAKMEM_FREE_PATH_STATS_BOX_H
|
|
|
|
#include <stdint.h>
|
|
#include <stdbool.h>
|
|
#include <stdlib.h>
|
|
|
|
typedef struct FreePathStats {
|
|
uint64_t total_calls;
|
|
|
|
uint64_t c7_ultra_fast;
|
|
uint64_t c6_ultra_free_fast; // Phase 4-2: C6 ULTRA-free
|
|
uint64_t c6_ultra_alloc_hit; // Phase 4-4: C6 ULTRA-alloc (TLS pop)
|
|
uint64_t c6_ifl_push; // Phase TLS-UNIFY-3: C6 intrusive push
|
|
uint64_t c6_ifl_pop; // Phase TLS-UNIFY-3: C6 intrusive pop
|
|
uint64_t c6_ifl_fallback; // Phase TLS-UNIFY-3: C6 intrusive fallback (slow)
|
|
uint64_t c5_ultra_free_fast; // Phase 5-1: C5 ULTRA-free
|
|
uint64_t c5_ultra_alloc_hit; // Phase 5-2: C5 ULTRA-alloc (TLS pop)
|
|
uint64_t c4_ultra_free_fast; // Phase 6: C4 ULTRA-free (cap=64)
|
|
uint64_t c4_ultra_alloc_hit; // Phase 6: C4 ULTRA-alloc (TLS pop)
|
|
uint64_t smallheap_v3_fast;
|
|
uint64_t smallheap_v6_fast;
|
|
uint64_t smallheap_v7_fast; // Phase v7-2: SmallHeap v7 fast free
|
|
uint64_t tiny_heap_v1_fast;
|
|
uint64_t pool_v1_fast;
|
|
uint64_t remote_free;
|
|
uint64_t super_lookup_called;
|
|
uint64_t legacy_fallback;
|
|
|
|
// Phase 4-1: Legacy per-class breakdown
|
|
uint64_t legacy_by_class[8]; // C0-C7 の Legacy fallback 内訳
|
|
|
|
// Phase POLICY-FAST-PATH-V2: Fast-path policy skip
|
|
uint64_t policy_fast_v2_skip; // Phase POLICY-FAST-PATH-V2 fast-path skips
|
|
} FreePathStats;
|
|
|
|
// ENV gate
|
|
static inline bool free_path_stats_enabled(void) {
|
|
static int g_enabled = -1; // -1: unknown, 0: off, 1: on
|
|
static int g_probe_left = 64; // tolerate early getenv() instability (bench_profile putenv)
|
|
|
|
if (__builtin_expect(g_enabled == 1, 1)) return true;
|
|
if (__builtin_expect(g_enabled == 0, 1)) return false;
|
|
|
|
const char* e = getenv("HAKMEM_FREE_PATH_STATS");
|
|
if (e && *e) {
|
|
g_enabled = (*e != '0') ? 1 : 0;
|
|
return g_enabled == 1;
|
|
}
|
|
|
|
if (g_probe_left-- > 0) {
|
|
return false; // keep g_enabled==-1, retry later
|
|
}
|
|
|
|
g_enabled = 0;
|
|
return false;
|
|
}
|
|
|
|
// Global stats instance
|
|
extern FreePathStats g_free_path_stats;
|
|
|
|
// Increment macros (with unlikely guard)
|
|
#define FREE_PATH_STAT_INC(field) \
|
|
do { if (__builtin_expect(free_path_stats_enabled(), 0)) { \
|
|
g_free_path_stats.field++; \
|
|
} } while(0)
|
|
|
|
#endif // HAKMEM_FREE_PATH_STATS_BOX_H
|