Files
hakmem/core/hakmem_tiny_magazine.c

165 lines
5.9 KiB
C
Raw Normal View History

#include "hakmem_tiny_magazine.h"
#include "hakmem_tiny_config.h" // Centralized configuration
#include "hakmem_tiny.h" // For TINY_NUM_CLASSES
#include "hakmem_tiny_superslab.h"
#include "hakmem_super_registry.h" // Phase 1: For hak_super_lookup()
#include "tiny_remote.h"
#include "hakmem_prof.h"
#include "hakmem_internal.h"
Phase E3-FINAL: Fix Box API offset bugs - ALL classes now use correct offsets ## Root Cause Analysis (GPT5) **Physical Layout Constraints**: - Class 0: 8B = [1B header][7B payload] → offset 1 = 9B needed = ❌ IMPOSSIBLE - Class 1-6: >=16B = [1B header][15B+ payload] → offset 1 = ✅ POSSIBLE - Class 7: 1KB → offset 0 (compatibility) **Correct Specification**: - HAKMEM_TINY_HEADER_CLASSIDX != 0: - Class 0, 7: next at offset 0 (overwrites header when on freelist) - Class 1-6: next at offset 1 (after header) - HAKMEM_TINY_HEADER_CLASSIDX == 0: - All classes: next at offset 0 **Previous Bug**: - Attempted "ALL classes offset 1" unification - Class 0 with offset 1 caused immediate SEGV (9B > 8B block size) - Mixed 2-arg/3-arg API caused confusion ## Fixes Applied ### 1. Restored 3-Argument Box API (core/box/tiny_next_ptr_box.h) ```c // Correct signatures void tiny_next_write(int class_idx, void* base, void* next_value) void* tiny_next_read(int class_idx, const void* base) // Correct offset calculation size_t offset = (class_idx == 0 || class_idx == 7) ? 0 : 1; ``` ### 2. Updated 123+ Call Sites Across 34 Files - hakmem_tiny_hot_pop_v4.inc.h (4 locations) - hakmem_tiny_fastcache.inc.h (3 locations) - hakmem_tiny_tls_list.h (12 locations) - superslab_inline.h (5 locations) - tiny_fastcache.h (3 locations) - ptr_trace.h (macro definitions) - tls_sll_box.h (2 locations) - + 27 additional files Pattern: `tiny_next_read(base)` → `tiny_next_read(class_idx, base)` Pattern: `tiny_next_write(base, next)` → `tiny_next_write(class_idx, base, next)` ### 3. Added Sentinel Detection Guards - tiny_fast_push(): Block nodes with sentinel in ptr or ptr->next - tls_list_push(): Block nodes with sentinel in ptr or ptr->next - Defense-in-depth against remote free sentinel leakage ## Verification (GPT5 Report) **Test Command**: `./out/release/bench_random_mixed_hakmem --iterations=70000` **Results**: - ✅ Main loop completed successfully - ✅ Drain phase completed successfully - ✅ NO SEGV (previous crash at iteration 66151 is FIXED) - ℹ️ Final log: "tiny_alloc(1024) failed" is normal fallback to Mid/ACE layers **Analysis**: - Class 0 immediate SEGV: ✅ RESOLVED (correct offset 0 now used) - 66K iteration crash: ✅ RESOLVED (offset consistency fixed) - Box API conflicts: ✅ RESOLVED (unified 3-arg API) ## Technical Details ### Offset Logic Justification ``` Class 0: 8B block → next pointer (8B) fits ONLY at offset 0 Class 1: 16B block → next pointer (8B) fits at offset 1 (after 1B header) Class 2: 32B block → next pointer (8B) fits at offset 1 ... Class 6: 512B block → next pointer (8B) fits at offset 1 Class 7: 1024B block → offset 0 for legacy compatibility ``` ### Files Modified (Summary) - Core API: `box/tiny_next_ptr_box.h` - Hot paths: `hakmem_tiny_hot_pop*.inc.h`, `tiny_fastcache.h` - TLS layers: `hakmem_tiny_tls_list.h`, `hakmem_tiny_tls_ops.h` - SuperSlab: `superslab_inline.h`, `tiny_superslab_*.inc.h` - Refill: `hakmem_tiny_refill.inc.h`, `tiny_refill_opt.h` - Free paths: `tiny_free_magazine.inc.h`, `tiny_superslab_free.inc.h` - Documentation: Multiple Phase E3 reports ## Remaining Work None for Box API offset bugs - all structural issues resolved. Future enhancements (non-critical): - Periodic `grep -R '*(void**)' core/` to detect direct pointer access violations - Enforce Box API usage via static analysis - Document offset rationale in architecture docs 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-13 06:50:20 +09:00
#include "box/tiny_next_ptr_box.h" // Box API: Next pointer read/write
#include "box/tiny_mem_stats_box.h"
#include <pthread.h>
static inline uint32_t tiny_self_u32_guard(void) {
return (uint32_t)(uintptr_t)pthread_self();
}
static inline void superslab_dec_active_safe(SuperSlab* ss) {
if (!ss) return;
uint32_t old = atomic_load_explicit(&ss->total_active_blocks, memory_order_relaxed);
while (old != 0u) {
if (atomic_compare_exchange_weak_explicit(&ss->total_active_blocks,
&old,
old - 1u,
memory_order_relaxed,
memory_order_relaxed)) {
break;
}
}
}
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
__thread TinyTLSMag g_tls_mags[TINY_NUM_CLASSES] = {0};
// Global cap limiter (can be reduced via env HAKMEM_TINY_MAG_CAP)
int g_mag_cap_limit = TINY_TLS_MAG_CAP;
// Normal-path per-class overrides (env tunables)
int g_mag_cap_override[TINY_NUM_CLASSES] = {0}; // HAKMEM_TINY_MAG_CAP_C{0..7}
__thread int g_tls_small_mags_inited = 0;
static __thread int g_tls_mag_mem_recorded = 0;
static inline void tiny_mag_record_mem_once(void) {
if (!g_tls_mag_mem_recorded) {
tiny_mem_stats_add_tls_magazine((ssize_t)sizeof(g_tls_mags));
g_tls_mag_mem_recorded = 1;
}
}
// tiny_default_cap() and tiny_cap_max_for_class() now defined as inline functions
// in hakmem_tiny_config.h for centralized configuration
int tiny_effective_cap(int class_idx) {
// Env override takes precedence per class
int ov = g_mag_cap_override[class_idx];
if (ov > 0) return ov;
return tiny_default_cap(class_idx); // Use centralized config function
}
void tiny_small_mags_init_once(void) {
if (__builtin_expect(g_tls_small_mags_inited, 1)) return;
tiny_mag_record_mem_once();
for (int k = 0; k <= 3; k++) {
TinyTLSMag* m = &g_tls_mags[k];
if (m->cap == 0) {
int base = tiny_effective_cap(k);
int cap = (base < TINY_TLS_MAG_CAP) ? base : TINY_TLS_MAG_CAP;
if (g_mag_cap_limit < cap) cap = g_mag_cap_limit;
m->cap = cap;
m->top = 0;
}
}
g_tls_small_mags_inited = 1;
}
void tiny_mag_init_if_needed(int class_idx) {
TinyTLSMag* mag = &g_tls_mags[class_idx];
if (mag->cap == 0) {
tiny_mag_record_mem_once();
int base = tiny_effective_cap(class_idx);
int cap = (base < TINY_TLS_MAG_CAP) ? base : TINY_TLS_MAG_CAP;
if (g_mag_cap_limit < cap) cap = g_mag_cap_limit;
mag->cap = cap;
mag->top = 0;
}
}
// ============================================================================
// ACE Learning Layer: Runtime TLS Capacity Adjustment
// ============================================================================
void hkm_ace_set_tls_capacity(int class_idx, uint32_t capacity) {
// Validate inputs
if (class_idx < 0 || class_idx >= TINY_NUM_CLASSES) {
return;
}
if (capacity < 16 || capacity > (uint32_t)tiny_cap_max_for_class(class_idx)) {
return;
}
// Set override (will be used by new thread-local magazines on next init)
// Note: Lazy sync implementation is in hakmem_tiny_magazine.h (inlined)
g_mag_cap_override[class_idx] = (int)capacity;
}
// ============================================================================
// Phase 7.7: Magazine Flush API
// ============================================================================
// Flush Magazine cache for a specific size class
// Forces all cached blocks to be returned to freelists, enabling empty
// SuperSlab detection and deallocation
void hak_tiny_magazine_flush(int class_idx) {
if (class_idx < 0 || class_idx >= TINY_NUM_CLASSES) return;
// Initialize if needed
tiny_mag_init_if_needed(class_idx);
TinyTLSMag* mag = &g_tls_mags[class_idx];
if (mag->top == 0) return; // Nothing to flush
// Lock and flush entire Magazine to freelist
pthread_mutex_t* lock = &g_tiny_class_locks[class_idx].m;
struct timespec tss; int ss_time = hkm_prof_begin(&tss);
(void)ss_time; (void)tss;
pthread_mutex_lock(lock);
// Flush ALL blocks (not just half like normal spill)
int flush_count = mag->top;
uint32_t self_tid = tiny_self_u32_guard();
for (int i = 0; i < flush_count; i++) {
TinyMagItem it = mag->items[--mag->top];
// Return to SuperSlab freelist
SuperSlab* owner_ss = hak_super_lookup(it.ptr);
if (owner_ss && owner_ss->magic == SUPERSLAB_MAGIC) {
int slab_idx = slab_index_for(owner_ss, it.ptr);
TinySlabMeta* meta = &owner_ss->slabs[slab_idx];
if (!tiny_remote_guard_allow_local_push(owner_ss, slab_idx, meta, it.ptr, "mag_flush", self_tid)) {
(void)ss_remote_push(owner_ss, slab_idx, it.ptr);
if (meta->used > 0) meta->used--;
continue;
}
Phase 12: Shared SuperSlab Pool implementation (WIP - runtime crash) ## Summary Implemented Phase 12 Shared SuperSlab Pool (mimalloc-style) to address SuperSlab allocation churn (877 SuperSlabs → 100-200 target). ## Implementation (ChatGPT + Claude) 1. **Metadata changes** (superslab_types.h): - Added class_idx to TinySlabMeta (per-slab dynamic class) - Removed size_class from SuperSlab (no longer per-SuperSlab) - Changed owner_tid (16-bit) → owner_tid_low (8-bit) 2. **Shared Pool** (hakmem_shared_pool.{h,c}): - Global pool shared by all size classes - shared_pool_acquire_slab() - Get free slab for class_idx - shared_pool_release_slab() - Return slab when empty - Per-class hints for fast path optimization 3. **Integration** (23 files modified): - Updated all ss->size_class → meta->class_idx - Updated all meta->owner_tid → meta->owner_tid_low - superslab_refill() now uses shared pool - Free path releases empty slabs back to pool 4. **Build system** (Makefile): - Added hakmem_shared_pool.o to OBJS_BASE and TINY_BENCH_OBJS_BASE ## Status: ⚠️ Build OK, Runtime CRASH **Build**: ✅ SUCCESS - All 23 files compile without errors - Only warnings: superslab_allocate type mismatch (legacy code) **Runtime**: ❌ SEGFAULT - Crash location: sll_refill_small_from_ss() - Exit code: 139 (SIGSEGV) - Test case: ./bench_random_mixed_hakmem 1000 256 42 ## Known Issues 1. **SEGFAULT in refill path** - Likely shared_pool_acquire_slab() issue 2. **Legacy superslab_allocate()** still exists (type mismatch warning) 3. **Remaining TODOs** from design doc: - SuperSlab physical layout integration - slab_handle.h cleanup - Remove old per-class head implementation ## Next Steps 1. Debug SEGFAULT (gdb backtrace shows sll_refill_small_from_ss) 2. Fix shared_pool_acquire_slab() or superslab_init_slab() 3. Basic functionality test (1K → 100K iterations) 4. Measure SuperSlab count reduction (877 → 100-200) 5. Performance benchmark (+650-860% expected) ## Files Changed (25 files) core/box/free_local_box.c core/box/free_remote_box.c core/box/front_gate_classifier.c core/hakmem_super_registry.c core/hakmem_tiny.c core/hakmem_tiny_bg_spill.c core/hakmem_tiny_free.inc core/hakmem_tiny_lifecycle.inc core/hakmem_tiny_magazine.c core/hakmem_tiny_query.c core/hakmem_tiny_refill.inc.h core/hakmem_tiny_superslab.c core/hakmem_tiny_superslab.h core/hakmem_tiny_tls_ops.h core/slab_handle.h core/superslab/superslab_inline.h core/superslab/superslab_types.h core/tiny_debug.h core/tiny_free_fast.inc.h core/tiny_free_magazine.inc.h core/tiny_remote.c core/tiny_superslab_alloc.inc.h core/tiny_superslab_free.inc.h Makefile ## New Files (3 files) PHASE12_SHARED_SUPERSLAB_POOL_DESIGN.md core/hakmem_shared_pool.c core/hakmem_shared_pool.h 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: ChatGPT <chatgpt@openai.com>
2025-11-13 16:33:03 +09:00
uint8_t cls = (meta->class_idx < TINY_NUM_CLASSES) ? meta->class_idx : (uint8_t)class_idx;
tiny_next_write(cls, it.ptr, meta->freelist);
meta->freelist = it.ptr;
meta->used--;
// Active was decremented at free time
// 空検出・解放はフラッシュ系APIへ委譲ホットパス除外
}
}
pthread_mutex_unlock(lock);
hkm_prof_end(ss_time, HKP_TINY_SPILL, &tss);
}
// Flush all Magazine caches
// Call this when memory needs to be released (e.g., before measuring RSS)
void hak_tiny_magazine_flush_all(void) {
for (int i = 0; i < TINY_NUM_CLASSES; i++) {
hak_tiny_magazine_flush(i);
}
hak_tiny_trim();
}