Files
hakmem/core/hakmem_tiny_slow.inc

99 lines
4.2 KiB
PHP
Raw Normal View History

// hakmem_tiny_slow.inc
// Slow path allocation implementation
// Slow path allocation function
// Phase 6-1.7: Export for box refactor (Box 5 needs access from hakmem.c)
#ifdef HAKMEM_TINY_PHASE6_BOX_REFACTOR
void* __attribute__((cold, noinline)) hak_tiny_alloc_slow(size_t size, int class_idx) {
#else
static void* __attribute__((cold, noinline)) hak_tiny_alloc_slow(size_t size, int class_idx) {
#endif
(void)size; // size is already validated by caller
if (class_idx < 0 || class_idx >= TINY_NUM_CLASSES) {
return NULL;
}
// Try refilling from HotMag
if (g_hotmag_enable && class_idx <= 3) {
TinyHotMag* hm = &g_tls_hot_mag[class_idx];
hotmag_try_refill(class_idx, hm);
void* ptr = hotmag_pop(class_idx);
if (ptr) { HAK_RET_ALLOC(class_idx, ptr); }
}
// Try TLS list refill
if (g_tls_list_enable) {
TinyTLSList* tls = &g_tls_lists[class_idx];
if (tls->count > 0) {
void* ptr = tls_list_pop(tls);
if (ptr) { HAK_RET_ALLOC(class_idx, ptr); }
// ptr が NULL の場合でも、ここで終了せず後段の Superslab 経路へフォールバックする
}
// Try refilling TLS list from slab
uint32_t want = tls->refill_low > 0 ? tls->refill_low : 32;
if (tls_refill_from_tls_slab(class_idx, tls, want) > 0) {
void* ptr = tls_list_pop(tls);
if (ptr) { HAK_RET_ALLOC(class_idx, ptr); }
// ここでも NULL の場合は続行(後段へフォールバック)
}
}
CRITICAL FIX: TLS 未初期化による 4T SEGV を完全解消 **問題:** - Larson 4T で 100% SEGV (1T は 2.09M ops/s で完走) - System/mimalloc は 4T で 33.52M ops/s 正常動作 - SS OFF + Remote OFF でも 4T で SEGV **根本原因: (Task agent ultrathink 調査結果)** ``` CRASH: mov (%r15),%r13 R15 = 0x6261 ← ASCII "ba" (ゴミ値、未初期化TLS) ``` Worker スレッドの TLS 変数が未初期化: - `__thread void* g_tls_sll_head[TINY_NUM_CLASSES];` ← 初期化なし - pthread_create() で生成されたスレッドでゼロ初期化されない - NULL チェックが通過 (0x6261 != NULL) → dereference → SEGV **修正内容:** 全 TLS 配列に明示的初期化子 `= {0}` を追加: 1. **core/hakmem_tiny.c:** - `g_tls_sll_head[TINY_NUM_CLASSES] = {0}` - `g_tls_sll_count[TINY_NUM_CLASSES] = {0}` - `g_tls_live_ss[TINY_NUM_CLASSES] = {0}` - `g_tls_bcur[TINY_NUM_CLASSES] = {0}` - `g_tls_bend[TINY_NUM_CLASSES] = {0}` 2. **core/tiny_fastcache.c:** - `g_tiny_fast_cache[TINY_FAST_CLASS_COUNT] = {0}` - `g_tiny_fast_count[TINY_FAST_CLASS_COUNT] = {0}` - `g_tiny_fast_free_head[TINY_FAST_CLASS_COUNT] = {0}` - `g_tiny_fast_free_count[TINY_FAST_CLASS_COUNT] = {0}` 3. **core/hakmem_tiny_magazine.c:** - `g_tls_mags[TINY_NUM_CLASSES] = {0}` 4. **core/tiny_sticky.c:** - `g_tls_sticky_ss[TINY_NUM_CLASSES][TINY_STICKY_RING] = {0}` - `g_tls_sticky_idx[TINY_NUM_CLASSES][TINY_STICKY_RING] = {0}` - `g_tls_sticky_pos[TINY_NUM_CLASSES] = {0}` **効果:** ``` Before: 1T: 2.09M ✅ | 4T: SEGV 💀 After: 1T: 2.41M ✅ | 4T: 4.19M ✅ (+15% 1T, SEGV解消) ``` **テスト:** ```bash # 1 thread: 完走 ./larson_hakmem 2 8 128 1024 1 12345 1 → Throughput = 2,407,597 ops/s ✅ # 4 threads: 完走(以前は SEGV) ./larson_hakmem 2 8 128 1024 1 12345 4 → Throughput = 4,192,155 ops/s ✅ ``` **調査協力:** Task agent (ultrathink mode) による完璧な根本原因特定 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-07 01:27:04 +09:00
// Background coalescing/aggregation (ENV gated, very lightweight)
do {
// BG Remote Drain (coalescer)
static int bg_en = -1, bg_period = -1, bg_budget = -1;
static __thread uint32_t bg_tick[8];
if (__builtin_expect(bg_en == -1, 0)) {
const char* e = getenv("HAKMEM_TINY_BG_REMOTE");
bg_en = (e && *e && *e != '0') ? 1 : 0;
const char* p = getenv("HAKMEM_TINY_BG_REMOTE_PERIOD");
bg_period = p ? atoi(p) : 1024;
if (bg_period <= 0) bg_period = 1024;
const char* b = getenv("HAKMEM_TINY_BG_REMOTE_BATCH");
bg_budget = b ? atoi(b) : 4;
if (bg_budget < 0) bg_budget = 0; if (bg_budget > 64) bg_budget = 64;
}
if (bg_en) {
if ((++bg_tick[class_idx] % (uint32_t)bg_period) == 0u) {
extern void tiny_remote_bg_drain_step(int class_idx, int budget);
tiny_remote_bg_drain_step(class_idx, bg_budget);
}
}
// Ready Aggregator (mailbox → ready push)
static int rdy_en = -1, rdy_period = -1, rdy_budget = -1;
static __thread uint32_t rdy_tick[8];
if (__builtin_expect(rdy_en == -1, 0)) {
const char* e = getenv("HAKMEM_TINY_BG_READY");
rdy_en = (e && *e && *e != '0') ? 1 : 0;
const char* p = getenv("HAKMEM_TINY_BG_READY_PERIOD");
rdy_period = p ? atoi(p) : 1024;
if (rdy_period <= 0) rdy_period = 1024;
const char* b = getenv("HAKMEM_TINY_BG_READY_BUDGET");
rdy_budget = b ? atoi(b) : 1;
if (rdy_budget < 0) rdy_budget = 0; if (rdy_budget > 8) rdy_budget = 8;
}
if (rdy_en) {
if ((++rdy_tick[class_idx] % (uint32_t)rdy_period) == 0u) {
extern void tiny_ready_bg_aggregate_step(int class_idx, int mail_budget);
tiny_ready_bg_aggregate_step(class_idx, rdy_budget);
}
}
} while (0);
// Final fallback: allocate from superslab
void* ss_ptr = hak_tiny_alloc_superslab(class_idx);
if (ss_ptr) { HAK_RET_ALLOC(class_idx, ss_ptr); }
tiny_alloc_dump_tls_state(class_idx, "slow_fail", &g_tls_slabs[class_idx]);
// Optional one-shot debug when final slow path fails
static int g_alloc_dbg = -1; if (__builtin_expect(g_alloc_dbg == -1, 0)) { const char* e=getenv("HAKMEM_TINY_ALLOC_DEBUG"); g_alloc_dbg = (e && atoi(e)!=0)?1:0; }
if (g_alloc_dbg) {
static _Atomic int printed[8]; int exp=0;
if (atomic_compare_exchange_strong(&printed[class_idx], &exp, 1)) {
fprintf(stderr, "[ALLOC-SLOW] hak_tiny_alloc_superslab returned NULL class=%d size=%zu\n", class_idx, size);
}
}
return ss_ptr;
}