// tiny_adaptive_sizing.c - Phase 2b: TLS Cache Adaptive Sizing Implementation
// Purpose: Hot classes get more cache → Better hit rate → Higher throughput

#include "tiny_adaptive_sizing.h"
#include "hakmem_tiny.h"
#include "box/tiny_next_ptr_box.h"  // Phase E1-CORRECT: Box API
#include <stdio.h>
#include <stdlib.h>

// TLS per-thread stats
__thread TLSCacheStats g_tls_cache_stats[TINY_NUM_CLASSES];

// Global enable flag (default: enabled, can disable via env)
int g_adaptive_sizing_enabled = 1;

// Logging enable flag (default: disabled; enable via HAKMEM_ADAPTIVE_LOG=1)
static int g_adaptive_logging_enabled = 0;

// Forward declaration for draining blocks
extern void tiny_superslab_return_block(void* ptr, int class_idx);
extern int hak_tiny_size_to_class(size_t size);

// ========== Initialization ==========

void adaptive_sizing_init(void) {
    // Read environment variable
    const char* env = getenv("HAKMEM_ADAPTIVE_SIZING");
    if (env && atoi(env) == 0) {
        g_adaptive_sizing_enabled = 0;
        fprintf(stderr, "[ADAPTIVE] Adaptive sizing disabled via env\n");
        return;
    }

    // Read logging flag
    const char* log_env = getenv("HAKMEM_ADAPTIVE_LOG");
    if (log_env && atoi(log_env) == 0) {
        g_adaptive_logging_enabled = 0;
    }

    // Initialize stats for each class
    for (int class_idx = 0; class_idx < TINY_NUM_CLASSES; class_idx++) {
        TLSCacheStats* stats = &g_tls_cache_stats[class_idx];
        stats->capacity = TLS_CACHE_INITIAL_CAPACITY;  // Start with 64 slots
        stats->high_water_mark = 0;
        stats->refill_count = 0;
        stats->shrink_count = 0;
        stats->grow_count = 0;
        stats->last_adapt_time = get_timestamp_ns();
    }

    if (g_adaptive_logging_enabled) {
        fprintf(stderr, "[ADAPTIVE] Adaptive sizing initialized (initial_cap=%d, min=%d, max=%d)\n",
                TLS_CACHE_INITIAL_CAPACITY, TLS_CACHE_MIN_CAPACITY, TLS_CACHE_MAX_CAPACITY);
    }
}

// ========== Grow/Shrink Functions ==========

void grow_tls_cache(int class_idx) {
    TLSCacheStats* stats = &g_tls_cache_stats[class_idx];

    // Phase 10: Aggressive growth - add 50% instead of doubling
    // This allows more gradual growth to match actual demand
    size_t new_capacity = stats->capacity + (stats->capacity / 2);
    if (new_capacity > TLS_CACHE_MAX_CAPACITY) {
        new_capacity = TLS_CACHE_MAX_CAPACITY;
    }

    if (new_capacity == stats->capacity) {
        return;  // Already at max
    }

    size_t old_capacity = stats->capacity;
    stats->capacity = new_capacity;
    stats->grow_count++;

    if (g_adaptive_logging_enabled) {
        fprintf(stderr, "[TLS_CACHE] Grow class %d: %zu → %zu slots (+50%%, grow_count=%zu)\n",
                class_idx, old_capacity, stats->capacity, stats->grow_count);
    }
}

void drain_excess_blocks(int class_idx, int count) {
    void** head = &g_tls_sll[class_idx].head;
    int drained = 0;

    while (*head && drained < count) {
        void* block = *head;
        *head = tiny_next_read(class_idx, block);  // Pop from TLS list

        // Return to SuperSlab (best effort - ignore failures)
        // Note: tiny_superslab_return_block may not exist, use simpler approach
        // Just drop the blocks for now (they'll be reclaimed by OS eventually)
        // TODO: Integrate with proper SuperSlab return path

        drained++;
        if (g_tls_sll[class_idx].count > 0) {
            g_tls_sll[class_idx].count--;
        }
    }

    if (g_adaptive_logging_enabled && drained > 0) {
        fprintf(stderr, "[TLS_CACHE] Drained %d excess blocks from class %d\n", drained, class_idx);
    }
}

void shrink_tls_cache(int class_idx) {
    TLSCacheStats* stats = &g_tls_cache_stats[class_idx];

    size_t new_capacity = stats->capacity / 2;
    if (new_capacity < TLS_CACHE_MIN_CAPACITY) {
        new_capacity = TLS_CACHE_MIN_CAPACITY;
    }

    if (new_capacity == stats->capacity) {
        return;  // Already at min
    }

    // Evict excess blocks if current count > new_capacity
    if (g_tls_sll[class_idx].count > new_capacity) {
        int excess = (int)(g_tls_sll[class_idx].count - new_capacity);
        drain_excess_blocks(class_idx, excess);
    }

    size_t old_capacity = stats->capacity;
    stats->capacity = new_capacity;
    stats->shrink_count++;

    if (g_adaptive_logging_enabled) {
        fprintf(stderr, "[TLS_CACHE] Shrink class %d: %zu → %zu slots (shrink_count=%zu)\n",
                class_idx, old_capacity, stats->capacity, stats->shrink_count);
    }
}

// ========== Adaptation Logic ==========

void adapt_tls_cache_size(int class_idx) {
    if (!g_adaptive_sizing_enabled) return;

    TLSCacheStats* stats = &g_tls_cache_stats[class_idx];

    // Adapt every N refills or M seconds
    uint64_t now = get_timestamp_ns();
    int should_adapt = (stats->refill_count >= ADAPT_REFILL_THRESHOLD) ||
                        ((now - stats->last_adapt_time) >= ADAPT_TIME_THRESHOLD_NS);

    if (!should_adapt) {
        return;  // Too soon to adapt
    }

    // Avoid division by zero
    if (stats->capacity == 0) {
        stats->capacity = TLS_CACHE_INITIAL_CAPACITY;
        return;
    }

    // Calculate usage ratio
    double usage_ratio = (double)stats->high_water_mark / (double)stats->capacity;

    // Decide: grow, shrink, or keep
    if (usage_ratio > GROW_THRESHOLD) {
        // High usage (>80%) → grow cache
        grow_tls_cache(class_idx);
    } else if (usage_ratio < SHRINK_THRESHOLD) {
        // Low usage (<20%) → shrink cache
        shrink_tls_cache(class_idx);
    } else {
        // Moderate usage (20-80%) → keep current size
        if (g_adaptive_logging_enabled) {
            fprintf(stderr, "[TLS_CACHE] Keep class %d at %zu slots (usage=%.1f%%)\n",
                    class_idx, stats->capacity, usage_ratio * 100.0);
        }
    }

    // Reset stats for next window
    stats->high_water_mark = g_tls_sll[class_idx].count;
    stats->refill_count = 0;
    stats->last_adapt_time = now;
}