acc64f2438
## Summary - ChatGPT により bench_profile.h の setenv segfault を修正（RTLD_NEXT 経由に切り替え） - core/box/pool_zero_mode_box.h 新設：ENV キャッシュ経由で ZERO_MODE を統一管理 - core/hakmem_pool.c で zero mode に応じた memset 制御（FULL/header/off） - A/B テスト結果：ZERO_MODE=header で +15.34% improvement（1M iterations, C6-heavy） ## Files Modified - core/box/pool_api.inc.h: pool_zero_mode_box.h include - core/bench_profile.h: glibc setenv → malloc+putenv（segfault 回避） - core/hakmem_pool.c: zero mode 参照・制御ロジック - core/box/pool_zero_mode_box.h (新設): enum/getter - CURRENT_TASK.md: Phase ML1 結果記載 ## Test Results | Iterations | ZERO_MODE=full | ZERO_MODE=header | Improvement | |-----------|----------------|-----------------|------------| | 10K | 3.06 M ops/s | 3.17 M ops/s | +3.65% | | 1M | 23.71 M ops/s | 27.34 M ops/s | **+15.34%** | 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
85 lines
3.0 KiB
C
85 lines
3.0 KiB
C
// tiny_route.h - Route Fingerprint (Box-boundary tracing, ultra-light)
|
|
#pragma once
|
|
|
|
#include <stdint.h>
|
|
#include <stdlib.h>
|
|
#include <stdatomic.h>
|
|
#include "tiny_debug_ring.h"
|
|
|
|
// Bits (keep <= 63 to stay in one 64-bit word)
|
|
// 0: refill_enter
|
|
// 1/2: ready_try/ready_hit
|
|
// 3/4: mail_try/mail_hit
|
|
// 5/6: sticky_try/sticky_hit
|
|
// 7/8: hot_try/hot_hit
|
|
// 9/10: bench_try/bench_hit
|
|
// 11/12: reg_try/reg_hit
|
|
// 13/14: adopt_try/adopt_hit
|
|
// 15: mmap_path
|
|
// 16: free_enter
|
|
// 17: free_same_thread
|
|
// 18: free_remote_transition
|
|
// 19: first_free_transition
|
|
// 20: mailbox_publish
|
|
|
|
static __thread uint64_t g_route_fp __attribute__((unused));
|
|
static __thread uint32_t g_route_seq __attribute__((unused));
|
|
static __thread int g_route_active __attribute__((unused));
|
|
static int g_route_enable_env = -1;
|
|
static int g_route_sample_lg = -1;
|
|
|
|
static inline int route_enabled_runtime(void) {
|
|
if (__builtin_expect(g_route_enable_env == -1, 0)) {
|
|
const char* e = getenv("HAKMEM_ROUTE");
|
|
g_route_enable_env = (e && *e && *e != '0') ? 1 : 0;
|
|
}
|
|
return g_route_enable_env;
|
|
}
|
|
|
|
static inline uint32_t route_sample_mask(void) {
|
|
if (__builtin_expect(g_route_sample_lg == -1, 0)) {
|
|
const char* e = getenv("HAKMEM_ROUTE_SAMPLE_LG");
|
|
int lg = (e && *e) ? atoi(e) : 10; // 1/1024 既定
|
|
if (lg < 0) lg = 0;
|
|
if (lg > 24) lg = 24;
|
|
g_route_sample_lg = lg;
|
|
}
|
|
return (g_route_sample_lg >= 31) ? 0xFFFFFFFFu : ((1u << g_route_sample_lg) - 1u);
|
|
}
|
|
|
|
#if HAKMEM_BUILD_RELEASE && !HAKMEM_ROUTE
|
|
#define ROUTE_BEGIN(cls) do { (void)(cls); } while(0)
|
|
#define ROUTE_MARK(bit) do { (void)(bit); } while(0)
|
|
#define ROUTE_COMMIT(cls, tag) do { (void)(cls); (void)(tag); } while(0)
|
|
static inline void route_free_commit(int class_idx, uint64_t bits, uint16_t tag) {
|
|
(void)class_idx; (void)bits; (void)tag;
|
|
}
|
|
#else
|
|
#define ROUTE_BEGIN(cls) do { \
|
|
if (__builtin_expect(!route_enabled_runtime(), 1)) { g_route_active = 0; break; } \
|
|
uint32_t m = route_sample_mask(); \
|
|
uint32_t s = ++g_route_seq; \
|
|
g_route_active = ((s & m) == 0u); \
|
|
g_route_fp = 0ull; \
|
|
(void)(cls); \
|
|
} while(0)
|
|
|
|
#define ROUTE_MARK(bit) do { if (__builtin_expect(g_route_active, 0)) { g_route_fp |= (1ull << (bit)); } } while(0)
|
|
|
|
#define ROUTE_COMMIT(cls, tag) do { \
|
|
if (__builtin_expect(g_route_active, 0)) { \
|
|
uintptr_t aux = ((uintptr_t)(tag & 0xFFFF) << 48) | (uintptr_t)(g_route_fp & 0x0000FFFFFFFFFFFFull); \
|
|
tiny_debug_ring_record(TINY_RING_EVENT_ROUTE, (uint16_t)(cls), (void*)(uintptr_t)g_route_fp, aux); \
|
|
g_route_active = 0; \
|
|
} \
|
|
} while(0)
|
|
|
|
static inline void route_free_commit(int class_idx, uint64_t bits, uint16_t tag) {
|
|
if (!route_enabled_runtime()) return;
|
|
uintptr_t aux = ((uintptr_t)(tag & 0xFFFF) << 48) | (uintptr_t)(bits & 0x0000FFFFFFFFFFFFull);
|
|
tiny_debug_ring_record(TINY_RING_EVENT_ROUTE, (uint16_t)class_idx, (void*)(uintptr_t)bits, aux);
|
|
}
|
|
#endif
|
|
|
|
// Note: Build-time gate removed to keep integration simple; runtime env controls activation.
|