Files
hakmem/core/box/ss_hot_prewarm_box.c
Moe Charm (CI) 5b36c1c908 Phase 26: Front Gate Unification - Tiny allocator fast path (+12.9%)
Implementation:
- New single-layer malloc/free path for Tiny (≤1024B) allocations
- Bypasses 3-layer overhead: malloc → hak_alloc_at (236 lines) → wrapper → tiny_alloc_fast
- Leverages Phase 23 Unified Cache (tcache-style, 2-3 cache misses)
- Safe fallback to normal path on Unified Cache miss

Performance (Random Mixed 256B, 100K iterations):
- Baseline (Phase 26 OFF): 11.33M ops/s
- Phase 26 ON: 12.79M ops/s (+12.9%)
- Prediction (ChatGPT): +10-15% → Actual: +12.9% (perfect match!)

Bug fixes:
- Initialization bug: Added hak_init() call before fast path
- Page boundary SEGV: Added guard for offset_in_page == 0

Also includes Phase 23 debug log fixes:
- Guard C2_CARVE logs with #if !HAKMEM_BUILD_RELEASE
- Guard prewarm logs with #if !HAKMEM_BUILD_RELEASE
- Set Hot_2048 as default capacity (C2/C3=2048, others=64)

Files:
- core/front/malloc_tiny_fast.h: Phase 26 implementation (145 lines)
- core/box/hak_wrappers.inc.h: Fast path integration (+28 lines)
- core/front/tiny_unified_cache.h: Hot_2048 default
- core/tiny_refill_opt.h: C2_CARVE log guard
- core/box/ss_hot_prewarm_box.c: Prewarm log guard
- CURRENT_TASK.md: Phase 26 completion documentation

ENV variables:
- HAKMEM_FRONT_GATE_UNIFIED=1 (enable Phase 26, default: OFF)
- HAKMEM_TINY_UNIFIED_CACHE=1 (Phase 23, required)

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-17 05:29:08 +09:00

150 lines
4.9 KiB
C

// ss_hot_prewarm_box.c - Box SS-HotPrewarm Implementation
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "../hakmem_tiny.h" // MUST BE FIRST: Base types
#include "../hakmem_tiny_config.h" // TINY_NUM_CLASSES
#include "ss_hot_prewarm_box.h"
#include "prewarm_box.h" // box_prewarm_tls()
// Per-class prewarm targets (cached from ENV)
static int g_ss_hot_prewarm_targets[TINY_NUM_CLASSES] = {0};
static int g_ss_hot_prewarm_initialized = 0;
// Default aggressive targets (ChatGPT Phase 20 strategy)
// Classes 0-1 (tiny): 0 (no prewarm)
// Classes 2-3 (33-128B): 128 blocks (hot path)
// Classes 4-5 (129-512B): 64 blocks (medium hot)
// Classes 6-7 (513-1024B): 0 (rare)
static const int g_ss_hot_prewarm_defaults[TINY_NUM_CLASSES] = {
0, // C0 (16B) - not used
0, // C1 (17-32B) - not used
128, // C2 (33-64B) - HOT
128, // C3 (65-128B) - HOT
64, // C4 (129-256B) - MEDIUM
64, // C5 (257-512B) - MEDIUM
0, // C6 (513-1024B) - rare
0 // C7 (1024B) - rare
};
// ============================================================================
// Internal Helpers
// ============================================================================
static void ss_hot_prewarm_init_targets(void) {
if (g_ss_hot_prewarm_initialized) return;
// Step 1: Copy defaults
for (int i = 0; i < TINY_NUM_CLASSES; i++) {
g_ss_hot_prewarm_targets[i] = g_ss_hot_prewarm_defaults[i];
}
// Step 2: Check for global override
const char* all_env = getenv("HAKMEM_TINY_PREWARM_ALL");
if (all_env && *all_env) {
int all_count = atoi(all_env);
if (all_count >= 0) {
for (int i = 0; i < TINY_NUM_CLASSES; i++) {
g_ss_hot_prewarm_targets[i] = all_count;
}
#if !HAKMEM_BUILD_RELEASE
fprintf(stderr, "[BOX_SS_HOT_PREWARM] Global override: HAKMEM_TINY_PREWARM_ALL=%d\n", all_count);
#endif
}
}
// Step 3: Parse per-class ENV overrides
const char* class_env_names[TINY_NUM_CLASSES] = {
"HAKMEM_TINY_PREWARM_C0",
"HAKMEM_TINY_PREWARM_C1",
"HAKMEM_TINY_PREWARM_C2",
"HAKMEM_TINY_PREWARM_C3",
"HAKMEM_TINY_PREWARM_C4",
"HAKMEM_TINY_PREWARM_C5",
"HAKMEM_TINY_PREWARM_C6",
"HAKMEM_TINY_PREWARM_C7"
};
for (int i = 0; i < TINY_NUM_CLASSES; i++) {
const char* env = getenv(class_env_names[i]);
if (env && *env) {
int count = atoi(env);
if (count >= 0) {
g_ss_hot_prewarm_targets[i] = count;
#if !HAKMEM_BUILD_RELEASE
fprintf(stderr, "[BOX_SS_HOT_PREWARM] Class %d override: %s=%d\n",
i, class_env_names[i], count);
#endif
}
}
}
// Step 4: Report final configuration (debug only)
#if !HAKMEM_BUILD_RELEASE
fprintf(stderr, "[BOX_SS_HOT_PREWARM] Final targets: ");
for (int i = 0; i < TINY_NUM_CLASSES; i++) {
if (g_ss_hot_prewarm_targets[i] > 0) {
fprintf(stderr, "C%d=%d ", i, g_ss_hot_prewarm_targets[i]);
}
}
fprintf(stderr, "\n");
#endif
g_ss_hot_prewarm_initialized = 1;
}
// ============================================================================
// Public API
// ============================================================================
int box_ss_hot_prewarm_target(int class_idx) {
if (class_idx < 0 || class_idx >= TINY_NUM_CLASSES) return 0;
if (!g_ss_hot_prewarm_initialized) {
ss_hot_prewarm_init_targets();
}
return g_ss_hot_prewarm_targets[class_idx];
}
int box_ss_hot_prewarm_all(void) {
// Initialize targets from ENV
ss_hot_prewarm_init_targets();
int total_prewarmed = 0;
// Prewarm each class with non-zero target
for (int class_idx = 0; class_idx < TINY_NUM_CLASSES; class_idx++) {
int target = g_ss_hot_prewarm_targets[class_idx];
if (target <= 0) continue;
#if !HAKMEM_BUILD_RELEASE
fprintf(stderr, "[BOX_SS_HOT_PREWARM] Prewarming C%d with %d blocks...\n",
class_idx, target);
#endif
// Use Box Prewarm API to safely warm TLS SLL
// This will automatically:
// - Allocate SuperSlab if needed
// - Populate pages (touch memory)
// - Fill TLS SLL with blocks
int actual = box_prewarm_tls(class_idx, target);
#if !HAKMEM_BUILD_RELEASE
if (actual < target) {
fprintf(stderr, "[BOX_SS_HOT_PREWARM] C%d: requested=%d actual=%d (capacity limited)\n",
class_idx, target, actual);
}
#endif
total_prewarmed += actual;
}
// Phase 20-1: Log prewarm summary (DEBUG ONLY to avoid perf impact)
#if !HAKMEM_BUILD_RELEASE
fprintf(stderr, "[BOX_SS_HOT_PREWARM] Total blocks pre-warmed: %d\n", total_prewarmed);
#endif
return total_prewarmed;
}