hakmem/core/hakmem_tiny_lazy_init.inc.h

// hakmem_tiny_lazy_init.inc.h - Phase 22: Lazy Per-Class Initialization
// Goal: Reduce cold-start page faults by initializing only used classes
//
// ChatGPT Analysis (2025-11-16):
//   - hak_tiny_init() page faults: 94.94% of all page faults
//   - Cause: Eager init of all 8 classes even if only C2/C3 used
//   - Solution: Lazy init per class on first use
//
// Expected Impact:
//   - Page faults: -90% (only touch C2/C3 for 256B workload)
//   - Cold start: +30-40% performance (16.2M → 22-25M ops/s)

#ifndef HAKMEM_TINY_LAZY_INIT_INC_H
#define HAKMEM_TINY_LAZY_INIT_INC_H

#include <pthread.h>
#include <stdint.h>
#include <stdio.h>  // For fprintf
#include "superslab/superslab_types.h"  // For SuperSlabACEState
#include "box/ss_addr_map_box.h"  // Phase 9-1: SuperSlab address map

// ============================================================================
// Phase 22-1: Per-Class Initialization State
// ============================================================================

// Track which classes are initialized (per-thread)
__thread uint8_t g_class_initialized[TINY_NUM_CLASSES] = {0};

// Global one-time init flag (for shared resources)
static int g_tiny_global_initialized = 0;
static pthread_mutex_t g_lazy_init_lock = PTHREAD_MUTEX_INITIALIZER;

// ============================================================================
// Phase 22-2: Lazy Init Implementation
// ============================================================================

// Initialize one class lazily (called on first use)
static inline void lazy_init_class(int class_idx) {
    // Fast path: already initialized
    if (__builtin_expect(g_class_initialized[class_idx], 1)) {
        return;
    }

    // Slow path: need to initialize this class
    pthread_mutex_lock(&g_lazy_init_lock);

    // Double-check after acquiring lock
    if (g_class_initialized[class_idx]) {
        pthread_mutex_unlock(&g_lazy_init_lock);
        return;
    }

    // Extract from hak_tiny_init.inc lines 84-103: TLS List Init
    {
        TinyTLSList* tls = &g_tls_lists[class_idx];
        tls->head = NULL;
        tls->count = 0;
        uint32_t base_cap = (uint32_t)tiny_default_cap(class_idx);
        uint32_t class_max = (uint32_t)tiny_cap_max_for_class(class_idx);
        if (base_cap > class_max) base_cap = class_max;

        // Apply global cap limit if set
        extern int g_mag_cap_limit;
        extern int g_mag_cap_override[TINY_NUM_CLASSES];
        if ((uint32_t)g_mag_cap_limit < base_cap) base_cap = (uint32_t)g_mag_cap_limit;
        if (g_mag_cap_override[class_idx] > 0) {
            uint32_t ov = (uint32_t)g_mag_cap_override[class_idx];
            if (ov > class_max) ov = class_max;
            if (ov > (uint32_t)g_mag_cap_limit) ov = (uint32_t)g_mag_cap_limit;
            if (ov != 0u) base_cap = ov;
        }
        if (base_cap == 0u) base_cap = 32u;

        tls->cap = base_cap;
        tls->refill_low = tiny_tls_default_refill(base_cap);
        tls->spill_high = tiny_tls_default_spill(base_cap);
        tiny_tls_publish_targets(class_idx, base_cap);
    }

    // CRITICAL FIX: Clear TLS SLL (Phase 3d-B unified structure) to purge stale blocks
    // This prevents C7 1024B→2048B stride upgrade issues where old misaligned blocks
    // remain in TLS SLL from previous runs or initialization paths.
    // Note: g_tls_sll is defined in hakmem_tiny_tls_state_box.inc, already visible here
    g_tls_sll[class_idx].head = NULL;
    g_tls_sll[class_idx].count = 0;
#if !HAKMEM_BUILD_RELEASE
    fprintf(stderr, "[LAZY_INIT] Cleared TLS SLL for class %d (purge stale blocks)\n", class_idx);
#endif

    // Extract from hak_tiny_init.inc lines 623-625: Per-class lock
    pthread_mutex_init(&g_tiny_class_locks[class_idx].m, NULL);

    // Extract from hak_tiny_init.inc lines 628-637: ACE state
    {
        extern SuperSlabACEState g_ss_ace[TINY_NUM_CLASSES];
        g_ss_ace[class_idx].current_lg = 20;  // Start with 1MB SuperSlabs
        g_ss_ace[class_idx].target_lg = 20;
        g_ss_ace[class_idx].hot_score = 0;
        g_ss_ace[class_idx].alloc_count = 0;
        g_ss_ace[class_idx].refill_count = 0;
        g_ss_ace[class_idx].spill_count = 0;
        g_ss_ace[class_idx].live_blocks = 0;
        g_ss_ace[class_idx].last_tick_ns = 0;
    }

    // Mark as initialized
    g_class_initialized[class_idx] = 1;

    pthread_mutex_unlock(&g_lazy_init_lock);

#if !HAKMEM_BUILD_RELEASE
    fprintf(stderr, "[LAZY_INIT] Class %d initialized\n", class_idx);
#endif
}

// Global initialization (called once, for non-class resources)
static inline void lazy_init_global(void) {
    if (__builtin_expect(g_tiny_global_initialized, 1)) {
        return;
    }

    pthread_mutex_lock(&g_lazy_init_lock);

    if (g_tiny_global_initialized) {
        pthread_mutex_unlock(&g_lazy_init_lock);
        return;
    }

    // Initialize SuperSlab subsystem (only once)
    extern int g_use_superslab;
    if (g_use_superslab) {
        extern void hak_super_registry_init(void);
        extern void hak_ss_lru_init(void);
        extern void hak_ss_prewarm_init(void);

        hak_super_registry_init();
        hak_ss_lru_init();
        hak_ss_prewarm_init();

        // Phase 9-1: Initialize SuperSlab address map (hash table O(1) lookup)
        ss_map_init(&g_ss_addr_map);

#if !HAKMEM_BUILD_RELEASE
        if (getenv("HAKMEM_SS_MAP_TRACE")) {
            fprintf(stderr, "[SS_MAP] Initialized hash table with %d buckets\n", SS_MAP_HASH_SIZE);
        }
#endif
    }

    // Mark global resources as initialized
    g_tiny_global_initialized = 1;

    pthread_mutex_unlock(&g_lazy_init_lock);

#if !HAKMEM_BUILD_RELEASE
    fprintf(stderr, "[LAZY_INIT] Global resources initialized\n");
#endif
}

#endif // HAKMEM_TINY_LAZY_INIT_INC_H