2025-11-05 12:31:14 +09:00
|
|
|
// hakmem_tiny_fastcache.inc.h
|
|
|
|
|
// Phase 2D-1: Hot-path inline functions - Fast cache and quick slot operations
|
|
|
|
|
//
|
|
|
|
|
// This file contains fast cache and quick slot inline functions.
|
|
|
|
|
// These functions are extracted from hakmem_tiny.c to improve maintainability and
|
|
|
|
|
// reduce the main file size by approximately 53 lines.
|
|
|
|
|
//
|
|
|
|
|
// Functions handle:
|
|
|
|
|
// - tiny_fast_pop/push: Fast TLS cache operations (lines 377-404)
|
|
|
|
|
// - fastcache_pop/push: Frontend fast cache (lines 873-888)
|
|
|
|
|
// - quick_pop: Quick slot pop operation (line 892-896)
|
|
|
|
|
|
|
|
|
|
#ifndef HAKMEM_TINY_FASTCACHE_INC_H
|
|
|
|
|
#define HAKMEM_TINY_FASTCACHE_INC_H
|
|
|
|
|
|
|
|
|
|
#include "hakmem_tiny.h"
|
|
|
|
|
#include <stdint.h>
|
|
|
|
|
#include <stdlib.h>
|
|
|
|
|
#include <stdio.h>
|
|
|
|
|
#include <stdatomic.h>
|
|
|
|
|
|
|
|
|
|
// External TLS variables
|
|
|
|
|
extern int g_fast_enable;
|
|
|
|
|
extern uint16_t g_fast_cap[TINY_NUM_CLASSES];
|
|
|
|
|
extern __thread void* g_fast_head[TINY_NUM_CLASSES];
|
|
|
|
|
extern __thread uint16_t g_fast_count[TINY_NUM_CLASSES];
|
|
|
|
|
|
|
|
|
|
// Fast cache capacity
|
|
|
|
|
#define TINY_FASTCACHE_CAP 128
|
|
|
|
|
|
|
|
|
|
// Quick slot capacity
|
|
|
|
|
#define QUICK_CAP 6
|
|
|
|
|
|
|
|
|
|
// External variable declarations
|
|
|
|
|
// Note: TinyFastCache and TinyQuickSlot types must be defined before including this file
|
|
|
|
|
extern int g_fastcache_enable;
|
|
|
|
|
extern __thread TinyFastCache g_fast_cache[TINY_NUM_CLASSES];
|
|
|
|
|
extern int g_quick_enable;
|
|
|
|
|
extern __thread TinyQuickSlot g_tls_quick[TINY_NUM_CLASSES];
|
|
|
|
|
extern unsigned long long g_free_via_fastcache[];
|
|
|
|
|
extern unsigned long long g_fast_push_hits[];
|
|
|
|
|
extern unsigned long long g_fast_push_full[];
|
|
|
|
|
extern unsigned long long g_fast_push_disabled[];
|
|
|
|
|
extern unsigned long long g_fast_push_zero_cap[];
|
|
|
|
|
|
|
|
|
|
static int g_fast_debug_mode = -1;
|
|
|
|
|
static int g_fast_debug_limit = 8;
|
|
|
|
|
static _Atomic int g_fast_debug_seen[TINY_NUM_CLASSES];
|
|
|
|
|
|
|
|
|
|
static inline void tiny_fast_debug_log(int class_idx, const char* event, uint16_t count, uint16_t cap) {
|
|
|
|
|
if (__builtin_expect(g_fast_debug_mode == -1, 0)) {
|
|
|
|
|
const char* e = getenv("HAKMEM_TINY_FAST_DEBUG");
|
|
|
|
|
g_fast_debug_mode = (e && atoi(e) != 0) ? 1 : 0;
|
|
|
|
|
const char* limit_env = getenv("HAKMEM_TINY_FAST_DEBUG_MAX");
|
|
|
|
|
if (limit_env && *limit_env) {
|
|
|
|
|
int v = atoi(limit_env);
|
|
|
|
|
if (v > 0) g_fast_debug_limit = v;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
if (!g_fast_debug_mode) return;
|
|
|
|
|
int limit = g_fast_debug_limit;
|
|
|
|
|
if (limit <= 0) limit = 8;
|
|
|
|
|
int seen = atomic_fetch_add_explicit(&g_fast_debug_seen[class_idx], 1, memory_order_relaxed);
|
|
|
|
|
if (seen < limit) {
|
|
|
|
|
fprintf(stderr, "[FASTDBG] class=%d event=%s count=%u cap=%u\n",
|
|
|
|
|
class_idx, event, (unsigned)count, (unsigned)cap);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Tracepoint macros (no-op if not defined)
|
|
|
|
|
#ifndef HAK_TP1
|
|
|
|
|
#define HAK_TP1(name, idx) do { (void)(idx); } while(0)
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
// Basic fast cache operations
|
|
|
|
|
static inline __attribute__((always_inline)) void* tiny_fast_pop(int class_idx) {
|
|
|
|
|
if (!g_fast_enable) return NULL;
|
|
|
|
|
uint16_t cap = g_fast_cap[class_idx];
|
|
|
|
|
if (cap == 0) return NULL;
|
|
|
|
|
void* head = g_fast_head[class_idx];
|
|
|
|
|
if (!head) return NULL;
|
2025-11-10 18:04:08 +09:00
|
|
|
// Phase 7: header-aware next pointer (C0-C6: base+1, C7: base)
|
|
|
|
|
#if HAKMEM_TINY_HEADER_CLASSIDX
|
|
|
|
|
const size_t next_offset = (class_idx == 7) ? 0 : 1;
|
|
|
|
|
#else
|
|
|
|
|
const size_t next_offset = 0;
|
|
|
|
|
#endif
|
2025-11-11 21:49:05 +09:00
|
|
|
// Use safe unaligned load for "next" to avoid UB when offset==1
|
|
|
|
|
void* next = NULL;
|
|
|
|
|
{
|
|
|
|
|
#include "tiny_nextptr.h"
|
|
|
|
|
next = tiny_next_load(head, class_idx);
|
|
|
|
|
}
|
2025-11-05 12:31:14 +09:00
|
|
|
g_fast_head[class_idx] = next;
|
|
|
|
|
uint16_t count = g_fast_count[class_idx];
|
|
|
|
|
if (count > 0) {
|
|
|
|
|
g_fast_count[class_idx] = (uint16_t)(count - 1);
|
|
|
|
|
} else {
|
|
|
|
|
g_fast_count[class_idx] = 0;
|
|
|
|
|
}
|
Add Box 3 (Pointer Conversion Layer) and fix POOL_TLS_PHASE1 default
## Major Changes
### 1. Box 3: Pointer Conversion Module (NEW)
- File: core/box/ptr_conversion_box.h
- Purpose: Unified BASE ↔ USER pointer conversion (single source of truth)
- API: PTR_BASE_TO_USER(), PTR_USER_TO_BASE()
- Features: Zero-overhead inline, debug mode, NULL-safe, class 7 headerless support
- Design: Header-only, fully modular, no external dependencies
### 2. POOL_TLS_PHASE1 Default OFF (CRITICAL FIX)
- File: build.sh
- Change: POOL_TLS_PHASE1 now defaults to 0 (was hardcoded to 1)
- Impact: Eliminates pthread_mutex overhead on every free() (was causing 3.3x slowdown)
- Usage: Set POOL_TLS_PHASE1=1 env var to enable if needed
### 3. Pointer Conversion Fixes (PARTIAL)
- Files: core/box/front_gate_box.c, core/tiny_alloc_fast.inc.h, etc.
- Status: Partial implementation using Box 3 API
- Note: Work in progress, some conversions still need review
### 4. Performance Investigation Report (NEW)
- File: HOTPATH_PERFORMANCE_INVESTIGATION.md
- Findings:
- Hotpath works (+24% vs baseline) after POOL_TLS fix
- Still 9.2x slower than system malloc due to:
* Heavy initialization (23.85% of cycles)
* Syscall overhead (2,382 syscalls per 100K ops)
* Workload mismatch (C7 1KB is 49.8%, but only C5 256B has hotpath)
* 9.4x more instructions than system malloc
### 5. Known Issues
- SEGV at 20K-30K iterations (pre-existing bug, not related to pointer conversions)
- Root cause: Likely active counter corruption or TLS-SLL chain issues
- Status: Under investigation
## Performance Results (100K iterations, 256B)
- Baseline (Hotpath OFF): 7.22M ops/s
- Hotpath ON: 8.98M ops/s (+24% improvement ✓)
- System malloc: 82.2M ops/s (still 9.2x faster)
## Next Steps
- P0: Fix 20K-30K SEGV bug (GDB investigation needed)
- P1: Lazy initialization (+20-25% expected)
- P1: C7 (1KB) hotpath (+30-40% expected, biggest win)
- P2: Reduce syscalls (+15-20% expected)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-12 01:01:23 +09:00
|
|
|
// CRITICAL FIX: Convert base -> user pointer for classes 0-6
|
2025-11-10 16:48:20 +09:00
|
|
|
// Headerless class (1KB): clear embedded next pointer before returning to user
|
|
|
|
|
if (__builtin_expect(class_idx == 7, 0)) {
|
|
|
|
|
*(void**)head = NULL;
|
Add Box 3 (Pointer Conversion Layer) and fix POOL_TLS_PHASE1 default
## Major Changes
### 1. Box 3: Pointer Conversion Module (NEW)
- File: core/box/ptr_conversion_box.h
- Purpose: Unified BASE ↔ USER pointer conversion (single source of truth)
- API: PTR_BASE_TO_USER(), PTR_USER_TO_BASE()
- Features: Zero-overhead inline, debug mode, NULL-safe, class 7 headerless support
- Design: Header-only, fully modular, no external dependencies
### 2. POOL_TLS_PHASE1 Default OFF (CRITICAL FIX)
- File: build.sh
- Change: POOL_TLS_PHASE1 now defaults to 0 (was hardcoded to 1)
- Impact: Eliminates pthread_mutex overhead on every free() (was causing 3.3x slowdown)
- Usage: Set POOL_TLS_PHASE1=1 env var to enable if needed
### 3. Pointer Conversion Fixes (PARTIAL)
- Files: core/box/front_gate_box.c, core/tiny_alloc_fast.inc.h, etc.
- Status: Partial implementation using Box 3 API
- Note: Work in progress, some conversions still need review
### 4. Performance Investigation Report (NEW)
- File: HOTPATH_PERFORMANCE_INVESTIGATION.md
- Findings:
- Hotpath works (+24% vs baseline) after POOL_TLS fix
- Still 9.2x slower than system malloc due to:
* Heavy initialization (23.85% of cycles)
* Syscall overhead (2,382 syscalls per 100K ops)
* Workload mismatch (C7 1KB is 49.8%, but only C5 256B has hotpath)
* 9.4x more instructions than system malloc
### 5. Known Issues
- SEGV at 20K-30K iterations (pre-existing bug, not related to pointer conversions)
- Root cause: Likely active counter corruption or TLS-SLL chain issues
- Status: Under investigation
## Performance Results (100K iterations, 256B)
- Baseline (Hotpath OFF): 7.22M ops/s
- Hotpath ON: 8.98M ops/s (+24% improvement ✓)
- System malloc: 82.2M ops/s (still 9.2x faster)
## Next Steps
- P0: Fix 20K-30K SEGV bug (GDB investigation needed)
- P1: Lazy initialization (+20-25% expected)
- P1: C7 (1KB) hotpath (+30-40% expected, biggest win)
- P2: Reduce syscalls (+15-20% expected)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-12 01:01:23 +09:00
|
|
|
return head; // C7: return base (headerless)
|
2025-11-10 16:48:20 +09:00
|
|
|
}
|
Add Box 3 (Pointer Conversion Layer) and fix POOL_TLS_PHASE1 default
## Major Changes
### 1. Box 3: Pointer Conversion Module (NEW)
- File: core/box/ptr_conversion_box.h
- Purpose: Unified BASE ↔ USER pointer conversion (single source of truth)
- API: PTR_BASE_TO_USER(), PTR_USER_TO_BASE()
- Features: Zero-overhead inline, debug mode, NULL-safe, class 7 headerless support
- Design: Header-only, fully modular, no external dependencies
### 2. POOL_TLS_PHASE1 Default OFF (CRITICAL FIX)
- File: build.sh
- Change: POOL_TLS_PHASE1 now defaults to 0 (was hardcoded to 1)
- Impact: Eliminates pthread_mutex overhead on every free() (was causing 3.3x slowdown)
- Usage: Set POOL_TLS_PHASE1=1 env var to enable if needed
### 3. Pointer Conversion Fixes (PARTIAL)
- Files: core/box/front_gate_box.c, core/tiny_alloc_fast.inc.h, etc.
- Status: Partial implementation using Box 3 API
- Note: Work in progress, some conversions still need review
### 4. Performance Investigation Report (NEW)
- File: HOTPATH_PERFORMANCE_INVESTIGATION.md
- Findings:
- Hotpath works (+24% vs baseline) after POOL_TLS fix
- Still 9.2x slower than system malloc due to:
* Heavy initialization (23.85% of cycles)
* Syscall overhead (2,382 syscalls per 100K ops)
* Workload mismatch (C7 1KB is 49.8%, but only C5 256B has hotpath)
* 9.4x more instructions than system malloc
### 5. Known Issues
- SEGV at 20K-30K iterations (pre-existing bug, not related to pointer conversions)
- Root cause: Likely active counter corruption or TLS-SLL chain issues
- Status: Under investigation
## Performance Results (100K iterations, 256B)
- Baseline (Hotpath OFF): 7.22M ops/s
- Hotpath ON: 8.98M ops/s (+24% improvement ✓)
- System malloc: 82.2M ops/s (still 9.2x faster)
## Next Steps
- P0: Fix 20K-30K SEGV bug (GDB investigation needed)
- P1: Lazy initialization (+20-25% expected)
- P1: C7 (1KB) hotpath (+30-40% expected, biggest win)
- P2: Reduce syscalls (+15-20% expected)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-12 01:01:23 +09:00
|
|
|
// C0-C6: return user pointer (base+1)
|
|
|
|
|
return (void*)((uint8_t*)head + 1);
|
2025-11-05 12:31:14 +09:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline __attribute__((always_inline)) int tiny_fast_push(int class_idx, void* ptr) {
|
|
|
|
|
if (!g_fast_enable) {
|
|
|
|
|
g_fast_push_disabled[class_idx]++;
|
|
|
|
|
tiny_fast_debug_log(class_idx, "disabled", 0, 0);
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
uint16_t cap = g_fast_cap[class_idx];
|
|
|
|
|
if (cap == 0) {
|
|
|
|
|
g_fast_push_zero_cap[class_idx]++;
|
|
|
|
|
tiny_fast_debug_log(class_idx, "zero_cap", g_fast_count[class_idx], cap);
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
uint16_t count = g_fast_count[class_idx];
|
|
|
|
|
if (count >= cap) {
|
|
|
|
|
g_fast_push_full[class_idx]++;
|
|
|
|
|
tiny_fast_debug_log(class_idx, "full", count, cap);
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
2025-11-10 18:04:08 +09:00
|
|
|
// Phase 7: header-aware next pointer (C0-C6: base+1, C7: base)
|
|
|
|
|
#if HAKMEM_TINY_HEADER_CLASSIDX
|
|
|
|
|
const size_t next_offset2 = (class_idx == 7) ? 0 : 1;
|
|
|
|
|
#else
|
|
|
|
|
const size_t next_offset2 = 0;
|
|
|
|
|
#endif
|
2025-11-11 21:49:05 +09:00
|
|
|
{
|
|
|
|
|
#include "tiny_nextptr.h"
|
|
|
|
|
tiny_next_store(ptr, class_idx, g_fast_head[class_idx]);
|
|
|
|
|
}
|
2025-11-05 12:31:14 +09:00
|
|
|
g_fast_head[class_idx] = ptr;
|
|
|
|
|
g_fast_count[class_idx] = (uint16_t)(count + 1);
|
|
|
|
|
g_fast_push_hits[class_idx]++;
|
|
|
|
|
tiny_fast_debug_log(class_idx, "hit", (uint16_t)(count + 1), cap);
|
|
|
|
|
return 1;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Frontend fast cache operations
|
|
|
|
|
static inline void* fastcache_pop(int class_idx) {
|
|
|
|
|
TinyFastCache* fc = &g_fast_cache[class_idx];
|
|
|
|
|
if (__builtin_expect(fc->top > 0, 1)) {
|
Add Box 3 (Pointer Conversion Layer) and fix POOL_TLS_PHASE1 default
## Major Changes
### 1. Box 3: Pointer Conversion Module (NEW)
- File: core/box/ptr_conversion_box.h
- Purpose: Unified BASE ↔ USER pointer conversion (single source of truth)
- API: PTR_BASE_TO_USER(), PTR_USER_TO_BASE()
- Features: Zero-overhead inline, debug mode, NULL-safe, class 7 headerless support
- Design: Header-only, fully modular, no external dependencies
### 2. POOL_TLS_PHASE1 Default OFF (CRITICAL FIX)
- File: build.sh
- Change: POOL_TLS_PHASE1 now defaults to 0 (was hardcoded to 1)
- Impact: Eliminates pthread_mutex overhead on every free() (was causing 3.3x slowdown)
- Usage: Set POOL_TLS_PHASE1=1 env var to enable if needed
### 3. Pointer Conversion Fixes (PARTIAL)
- Files: core/box/front_gate_box.c, core/tiny_alloc_fast.inc.h, etc.
- Status: Partial implementation using Box 3 API
- Note: Work in progress, some conversions still need review
### 4. Performance Investigation Report (NEW)
- File: HOTPATH_PERFORMANCE_INVESTIGATION.md
- Findings:
- Hotpath works (+24% vs baseline) after POOL_TLS fix
- Still 9.2x slower than system malloc due to:
* Heavy initialization (23.85% of cycles)
* Syscall overhead (2,382 syscalls per 100K ops)
* Workload mismatch (C7 1KB is 49.8%, but only C5 256B has hotpath)
* 9.4x more instructions than system malloc
### 5. Known Issues
- SEGV at 20K-30K iterations (pre-existing bug, not related to pointer conversions)
- Root cause: Likely active counter corruption or TLS-SLL chain issues
- Status: Under investigation
## Performance Results (100K iterations, 256B)
- Baseline (Hotpath OFF): 7.22M ops/s
- Hotpath ON: 8.98M ops/s (+24% improvement ✓)
- System malloc: 82.2M ops/s (still 9.2x faster)
## Next Steps
- P0: Fix 20K-30K SEGV bug (GDB investigation needed)
- P1: Lazy initialization (+20-25% expected)
- P1: C7 (1KB) hotpath (+30-40% expected, biggest win)
- P2: Reduce syscalls (+15-20% expected)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-12 01:01:23 +09:00
|
|
|
void* base = fc->items[--fc->top];
|
|
|
|
|
// CRITICAL FIX: Convert base -> user pointer for classes 0-6
|
|
|
|
|
// FastCache stores base pointers, user needs base+1
|
|
|
|
|
if (class_idx == 7) {
|
|
|
|
|
return base; // C7: headerless, return base
|
|
|
|
|
}
|
|
|
|
|
return (void*)((uint8_t*)base + 1); // C0-C6: return user pointer
|
2025-11-05 12:31:14 +09:00
|
|
|
}
|
|
|
|
|
return NULL;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline int fastcache_push(int class_idx, void* ptr) {
|
|
|
|
|
TinyFastCache* fc = &g_fast_cache[class_idx];
|
|
|
|
|
if (__builtin_expect(fc->top < TINY_FASTCACHE_CAP, 1)) {
|
|
|
|
|
fc->items[fc->top++] = ptr;
|
|
|
|
|
g_free_via_fastcache[class_idx]++;
|
|
|
|
|
return 1;
|
|
|
|
|
}
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Quick slot pop operation
|
|
|
|
|
static inline void* quick_pop(int class_idx) {
|
|
|
|
|
TinyQuickSlot* qs = &g_tls_quick[class_idx];
|
|
|
|
|
if (__builtin_expect(qs->top > 0, 1)) {
|
|
|
|
|
void* p = qs->items[--qs->top];
|
|
|
|
|
HAK_TP1(quick_pop, class_idx);
|
|
|
|
|
return p;
|
|
|
|
|
}
|
|
|
|
|
return NULL;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#endif // HAKMEM_TINY_FASTCACHE_INC_H
|