Files
hakmem/core/box/hak_alloc_api.inc.h
Moe Charm (CI) ccccabd944 Phase 17-1: Small-Mid Allocator - TLS Frontend Cache (結果: ±0.3%, 層分離成功)
Summary:
========
Phase 17-1 implements Small-Mid allocator as TLS frontend cache with Tiny backend delegation.
Result: Clean layer separation achieved with minimal overhead (±0.3%), but no performance gain.
Conclusion: Frontend-only approach is dead end. Phase 17-2 (dedicated backend) required for 2-3x target.

Implementation:
===============
1. Small-Mid TLS frontend (256B/512B/1KB - 3 classes)
   - TLS freelist (32/24/16 capacity)
   - Backend delegation to Tiny C5/C6/C7
   - Header conversion (0xa0 → 0xb0)

2. Auto-adjust Tiny boundary
   - When Small-Mid ON: Tiny auto-limits to C0-C5 (0-255B)
   - When Small-Mid OFF: Tiny default C0-C7 (0-1023B)
   - Prevents routing conflict

3. Routing order fix
   - Small-Mid BEFORE Tiny (critical for proper execution)
   - Fall-through on TLS miss

Files Modified:
===============
- core/hakmem_smallmid.h/c: TLS freelist + backend delegation
- core/hakmem_tiny.c: tiny_get_max_size() auto-adjust
- core/box/hak_alloc_api.inc.h: Routing order (Small-Mid → Tiny)
- CURRENT_TASK.md: Phase 17-1 results + Phase 17-2 plan

A/B Benchmark Results:
======================
| Size   | Config A (OFF) | Config B (ON) | Delta    | % Change |
|--------|----------------|---------------|----------|----------|
| 256B   | 5.87M ops/s    | 6.06M ops/s   | +191K    | +3.3%    |
| 512B   | 6.02M ops/s    | 5.91M ops/s   | -112K    | -1.9%    |
| 1024B  | 5.58M ops/s    | 5.54M ops/s   | -35K     | -0.6%    |
| Overall| 5.82M ops/s    | 5.84M ops/s   | +20K     | +0.3%    |

Analysis:
=========
 SUCCESS: Clean layer separation (Small-Mid ↔ Tiny coexist)
 SUCCESS: Minimal overhead (±0.3% = measurement noise)
 FAIL: No performance gain (target was 2-4x)

Root Cause:
-----------
- Delegation overhead = TLS savings (net gain ≈ 0 instructions)
- Small-Mid TLS alloc: ~3-5 instructions
- Tiny backend delegation: ~3-5 instructions
- Header conversion: ~2 instructions
- No batching: 1:1 delegation to Tiny (no refill amortization)

Lessons Learned:
================
- Frontend-only approach ineffective (backend calls not reduced)
- Dedicated backend essential for meaningful improvement
- Clean separation achieved = solid foundation for Phase 17-2

Next Steps (Phase 17-2):
========================
- Dedicated Small-Mid SuperSlab backend (separate from Tiny)
- TLS batch refill (8-16 blocks per refill)
- Optimized 0xb0 header fast path (no delegation)
- Target: 12-15M ops/s (2.0-2.6x improvement)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-16 02:37:24 +09:00

239 lines
8.4 KiB
C

// hak_alloc_api.inc.h — Box: hak_alloc_at() implementation
#ifndef HAK_ALLOC_API_INC_H
#define HAK_ALLOC_API_INC_H
#include "../hakmem_tiny.h" // For tiny_get_max_size() (Phase 16)
#include "../hakmem_smallmid.h" // For Small-Mid Front Box (Phase 17-1)
#ifdef HAKMEM_POOL_TLS_PHASE1
#include "../pool_tls.h"
#endif
// Centralized OS mapping boundary to keep syscalls in one place
static inline void* hak_os_map_boundary(size_t size, uintptr_t site_id) {
#if HAKMEM_DEBUG_TIMING
HKM_TIME_START(t_mmap);
#endif
void* p = hak_alloc_mmap_impl(size);
#if HAKMEM_DEBUG_TIMING
HKM_TIME_END(HKM_CAT_SYSCALL_MMAP, t_mmap);
#endif
(void)site_id; // reserved for future accounting/learning
return p;
}
__attribute__((always_inline))
inline void* hak_alloc_at(size_t size, hak_callsite_t site) {
#if HAKMEM_DEBUG_TIMING
HKM_TIME_START(t0);
#endif
if (!g_initialized) hak_init();
uintptr_t site_id = (uintptr_t)site;
// Phase 17-1: Small-Mid Front Box (256B-1KB) - TRY FIRST!
// Strategy: Thin TLS cache layer, no backend (falls through on miss)
// ENV: HAKMEM_SMALLMID_ENABLE=1 to enable (default: OFF)
// CRITICAL: Must come BEFORE Tiny to avoid routing conflict
// When enabled, auto-adjusts Tiny to C0-C5 (0-255B only)
if (smallmid_is_enabled() && smallmid_is_in_range(size)) {
#if HAKMEM_DEBUG_TIMING
HKM_TIME_START(t_smallmid);
#endif
void* sm_ptr = smallmid_alloc(size);
#if HAKMEM_DEBUG_TIMING
HKM_TIME_END(HKM_CAT_TINY_ALLOC, t_smallmid);
#endif
if (sm_ptr) {
hkm_ace_track_alloc();
return sm_ptr;
}
// TLS miss: Fall through to Mid/ACE (Tiny skipped due to auto-adjust)
}
// Phase 16: Dynamic Tiny max size (ENV: HAKMEM_TINY_MAX_CLASS)
// Default: 1023B (C0-C7), reduced to 255B (C0-C5) when Small-Mid enabled
// Phase 17-1: Auto-adjusted to avoid overlap with Small-Mid
if (__builtin_expect(size <= tiny_get_max_size(), 1)) {
#if HAKMEM_DEBUG_TIMING
HKM_TIME_START(t_tiny);
#endif
void* tiny_ptr = NULL;
#ifdef HAKMEM_TINY_PHASE6_BOX_REFACTOR
tiny_ptr = hak_tiny_alloc_fast_wrapper(size);
#elif defined(HAKMEM_TINY_PHASE6_ULTRA_SIMPLE)
tiny_ptr = hak_tiny_alloc_ultra_simple(size);
#elif defined(HAKMEM_TINY_PHASE6_METADATA)
tiny_ptr = hak_tiny_alloc_metadata(size);
#else
tiny_ptr = hak_tiny_alloc(size);
#endif
#if HAKMEM_DEBUG_TIMING
HKM_TIME_END(HKM_CAT_TINY_ALLOC, t_tiny);
#endif
if (tiny_ptr) { hkm_ace_track_alloc(); return tiny_ptr; }
// PHASE 7 CRITICAL FIX: No malloc fallback for Tiny failures
// If Tiny fails for size <= tiny_get_max_size(), let it flow to Mid/ACE layers
// This prevents mixed HAKMEM/libc allocation bugs
#if HAKMEM_TINY_HEADER_CLASSIDX
if (!tiny_ptr && size <= tiny_get_max_size()) {
#if !HAKMEM_BUILD_RELEASE
// Tiny failed - log and continue to Mid/ACE (no early return!)
static int log_count = 0;
if (log_count < 3) {
fprintf(stderr, "[DEBUG] Phase 7: tiny_alloc(%zu) failed, trying Mid/ACE layers (no malloc fallback)\n", size);
log_count++;
}
#endif
// Continue to Mid allocation below (do NOT fallback to malloc!)
}
#else
#if !HAKMEM_BUILD_RELEASE
static int log_count = 0; if (log_count < 3) { fprintf(stderr, "[DEBUG] tiny_alloc(%zu) returned NULL, falling back\n", size); log_count++; }
#endif
#endif
}
hkm_size_hist_record(size);
#ifdef HAKMEM_POOL_TLS_PHASE1
// Phase 1: Ultra-fast Pool TLS for 8KB-52KB range
if (size >= 8192 && size <= 53248) {
void* pool_ptr = pool_alloc(size);
if (pool_ptr) return pool_ptr;
// Fall through to existing Mid allocator as fallback
}
#endif
if (__builtin_expect(mid_is_in_range(size), 0)) {
#if HAKMEM_DEBUG_TIMING
HKM_TIME_START(t_mid);
#endif
void* mid_ptr = mid_mt_alloc(size);
#if HAKMEM_DEBUG_TIMING
HKM_TIME_END(HKM_CAT_POOL_GET, t_mid);
#endif
if (mid_ptr) return mid_ptr;
}
#if HAKMEM_FEATURE_EVOLUTION
if (g_evo_sample_mask > 0) {
static _Atomic uint64_t tick_counter = 0;
if ((atomic_fetch_add(&tick_counter, 1) & g_evo_sample_mask) == 0) {
struct timespec now; clock_gettime(CLOCK_MONOTONIC, &now);
uint64_t now_ns = now.tv_sec * 1000000000ULL + now.tv_nsec;
if (hak_evo_tick(now_ns)) {
int new_strategy = hak_elo_select_strategy();
atomic_store(&g_cached_strategy_id, new_strategy);
}
}
}
#endif
size_t threshold;
if (HAK_ENABLED_LEARNING(HAKMEM_FEATURE_ELO)) {
int strategy_id = atomic_load(&g_cached_strategy_id);
threshold = hak_elo_get_threshold(strategy_id);
} else {
threshold = 2097152;
}
if (HAK_ENABLED_CACHE(HAKMEM_FEATURE_BIGCACHE) && size >= threshold) {
void* cached_ptr = NULL;
#if HAKMEM_DEBUG_TIMING
HKM_TIME_START(t_bc);
#endif
if (hak_bigcache_try_get(size, site_id, &cached_ptr)) {
#if HAKMEM_DEBUG_TIMING
HKM_TIME_END(HKM_CAT_BIGCACHE_GET, t_bc);
#endif
return cached_ptr;
}
#if HAKMEM_DEBUG_TIMING
HKM_TIME_END(HKM_CAT_BIGCACHE_GET, t_bc);
#endif
}
if (size >= 33000 && size <= 34000) {
fprintf(stderr, "[ALLOC] 33KB: TINY_MAX_SIZE=%d, threshold=%zu, condition=%d\n",
TINY_MAX_SIZE, threshold, (size > TINY_MAX_SIZE && size < threshold));
}
if (size > TINY_MAX_SIZE && size < threshold) {
if (size >= 33000 && size <= 34000) {
fprintf(stderr, "[ALLOC] 33KB: Calling hkm_ace_alloc\n");
}
const FrozenPolicy* pol = hkm_policy_get();
#if HAKMEM_DEBUG_TIMING
HKM_TIME_START(t_ace);
#endif
void* l1 = hkm_ace_alloc(size, site_id, pol);
#if HAKMEM_DEBUG_TIMING
HKM_TIME_END(HKM_CAT_POOL_GET, t_ace);
#endif
if (size >= 33000 && size <= 34000) {
fprintf(stderr, "[ALLOC] 33KB: hkm_ace_alloc returned %p\n", l1);
}
if (l1) return l1;
}
// PHASE 7 CRITICAL FIX: Handle allocation gap (1KB-8KB) when ACE is disabled
// Size range:
// 0-1024: Tiny allocator
// 1025-8191: Gap! (Mid starts at 8KB, ACE often disabled)
// 8KB-32KB: Mid allocator
// 32KB-2MB: ACE (if enabled, otherwise mmap)
// 2MB+: mmap
//
// Solution: Use mmap for gap when ACE failed (ACE disabled or OOM)
// Track final fallback mmaps globally
extern _Atomic uint64_t g_final_fallback_mmap_count;
void* ptr;
if (size >= threshold) {
// Large allocation (>= 2MB default): descend via single boundary
atomic_fetch_add(&g_final_fallback_mmap_count, 1);
ptr = hak_os_map_boundary(size, site_id);
} else if (size >= TINY_MAX_SIZE) {
// Mid-range allocation (1KB-2MB): try mmap as final fallback
// This handles the gap when ACE is disabled or failed
atomic_fetch_add(&g_final_fallback_mmap_count, 1);
static _Atomic int gap_alloc_count = 0;
int count = atomic_fetch_add(&gap_alloc_count, 1);
#if HAKMEM_DEBUG_VERBOSE
if (count < 3) fprintf(stderr, "[HAKMEM] INFO: mid-gap fallback size=%zu\n", size);
#endif
ptr = hak_os_map_boundary(size, site_id);
} else {
// Should never reach here (size <= TINY_MAX_SIZE should be handled by Tiny)
static _Atomic int oom_count = 0;
int count = atomic_fetch_add(&oom_count, 1);
if (count < 10) {
fprintf(stderr, "[HAKMEM] OOM: Unexpected allocation path for size=%zu, returning NULL\n", size);
fprintf(stderr, "[HAKMEM] (OOM count: %d) This should not happen!\n", count + 1);
}
#if HAKMEM_DEBUG_TIMING
HKM_TIME_START(t_malloc);
HKM_TIME_END(HKM_CAT_FALLBACK_MALLOC, t_malloc); // Keep timing for compatibility
#endif
errno = ENOMEM;
return NULL;
}
if (!ptr) return NULL;
if (g_evo_sample_mask > 0) { hak_evo_record_size(size); }
AllocHeader* hdr = (AllocHeader*)((char*)ptr - HEADER_SIZE);
if (hdr->magic != HAKMEM_MAGIC) { fprintf(stderr, "[hakmem] ERROR: Invalid magic in allocated header!\n"); return ptr; }
hdr->alloc_site = site_id;
hdr->class_bytes = (size >= threshold) ? threshold : 0;
#if HAKMEM_DEBUG_TIMING
HKM_TIME_END(HKM_CAT_HAK_ALLOC, t0);
#endif
return ptr;
}
#endif // HAK_ALLOC_API_INC_H