### Changes: - **Routing Counters**: Added per-thread counters in hakmem.c to track: - g_malloc_total_calls: Total malloc() invocations - g_malloc_tiny_size_match: Calls within tiny size range (<=128B) - g_malloc_fast_path_tried: Calls that attempted fast path - g_malloc_fast_path_null: Fast path returned NULL - g_malloc_slow_path: Calls routed to slow path - **Refill Success Tracking**: Added counters in tiny_fastcache.c: - g_refill_success_count: Full batch (16 blocks) - g_refill_partial_count: Partial batch (<16 blocks) - g_refill_fail_count: Zero blocks allocated - g_refill_total_blocks: Total blocks across all refills - **Profile Output Enhanced**: tiny_fast_print_profile() now shows: - Routing statistics (which path allocations take) - Refill success/failure breakdown - Average blocks per refill ### Key Findings: ✅ Fast path routing: 100% success (20,479/20,480 calls per thread) ✅ Refill success: 100% (1,285 refills, all 16 blocks each) ⚠️ Performance: Still only 1.68M ops/s vs System's 8.06M (20.8%) **Root Cause Confirmed**: - NOT a routing problem (100% reach fast path) - NOT a refill failure (100% success) - IS a structural performance issue (2,418 cycles avg for malloc) **Bottlenecks Identified**: 1. Fast path cache hits: ~2,418 cycles (vs tcache ~100 cycles) 2. Refill operations: ~39,938 cycles (expensive but infrequent) 3. Overall throughput: 4.8x slower than system malloc **Next Steps** (per LARSON_PERFORMANCE_ANALYSIS_2025_11_05.md): - Option B: Refill efficiency (batch allocation from SuperSlab) - Option C: Ultra-fast path redesign (tcache-equivalent) Related: LARSON_PERFORMANCE_ANALYSIS_2025_11_05.md
303 lines
11 KiB
C
303 lines
11 KiB
C
// tiny_fastcache.c - Slow path for Tiny Fast Cache (refill/drain)
|
||
// Phase 6-3: Refill from Magazine/SuperSlab when fast cache misses
|
||
|
||
#include "tiny_fastcache.h"
|
||
#include "hakmem_tiny.h"
|
||
#include "hakmem_tiny_superslab.h"
|
||
#include <stdio.h>
|
||
#include <stdlib.h>
|
||
|
||
// ========== TLS Cache Definitions ==========
|
||
// (Declared as extern in tiny_fastcache.h)
|
||
|
||
__thread void* g_tiny_fast_cache[TINY_FAST_CLASS_COUNT];
|
||
__thread uint32_t g_tiny_fast_count[TINY_FAST_CLASS_COUNT];
|
||
__thread int g_tiny_fast_initialized = 0;
|
||
|
||
// ========== Phase 6-7: Dual Free Lists (Phase 2) ==========
|
||
// Inspired by mimalloc's local/remote split design
|
||
// Separate alloc/free paths to reduce cache line bouncing
|
||
|
||
__thread void* g_tiny_fast_free_head[TINY_FAST_CLASS_COUNT]; // Free staging area
|
||
__thread uint32_t g_tiny_fast_free_count[TINY_FAST_CLASS_COUNT]; // Free count
|
||
|
||
// ========== External References ==========
|
||
|
||
// External references to existing Tiny infrastructure (from hakmem_tiny.c)
|
||
extern __thread void* g_tls_sll_head[];
|
||
extern __thread uint32_t g_tls_sll_count[];
|
||
extern int g_use_superslab;
|
||
|
||
// From hakmem_tiny.c
|
||
extern void* hak_tiny_alloc_slow(size_t size, int class_idx);
|
||
|
||
// ========== Batch Refill Configuration ==========
|
||
|
||
// How many blocks to refill per miss (batch amortization)
|
||
#ifndef TINY_FAST_REFILL_BATCH
|
||
#define TINY_FAST_REFILL_BATCH 16
|
||
#endif
|
||
|
||
// ========== Debug Counters ==========
|
||
|
||
static __thread uint64_t g_tiny_fast_refill_count = 0;
|
||
static __thread uint64_t g_tiny_fast_drain_count = 0;
|
||
|
||
// ========== RDTSC Cycle Profiling ==========
|
||
// Ultra-lightweight profiling using CPU Time-Stamp Counter (~10 cycles overhead)
|
||
|
||
#ifdef __x86_64__
|
||
static inline uint64_t rdtsc(void) {
|
||
unsigned int lo, hi;
|
||
__asm__ __volatile__ ("rdtsc" : "=a" (lo), "=d" (hi));
|
||
return ((uint64_t)hi << 32) | lo;
|
||
}
|
||
#else
|
||
static inline uint64_t rdtsc(void) { return 0; } // Fallback for non-x86
|
||
#endif
|
||
|
||
// Per-thread cycle counters (gated by HAKMEM_TINY_PROFILE env var)
|
||
// Declared as extern in tiny_fastcache.h for inline functions
|
||
__thread uint64_t g_tiny_malloc_count = 0;
|
||
__thread uint64_t g_tiny_malloc_cycles = 0;
|
||
__thread uint64_t g_tiny_free_count = 0;
|
||
__thread uint64_t g_tiny_free_cycles = 0;
|
||
__thread uint64_t g_tiny_refill_cycles = 0;
|
||
__thread uint64_t g_tiny_migration_count = 0;
|
||
__thread uint64_t g_tiny_migration_cycles = 0;
|
||
|
||
// Refill failure tracking
|
||
static __thread uint64_t g_refill_success_count = 0;
|
||
static __thread uint64_t g_refill_partial_count = 0; // Some blocks allocated
|
||
static __thread uint64_t g_refill_fail_count = 0; // Zero blocks allocated
|
||
static __thread uint64_t g_refill_total_blocks = 0; // Total blocks actually allocated
|
||
|
||
int g_profile_enabled = -1; // -1: uninitialized, 0: off, 1: on (extern in header)
|
||
|
||
static inline int profile_enabled(void) {
|
||
if (__builtin_expect(g_profile_enabled == -1, 0)) {
|
||
const char* env = getenv("HAKMEM_TINY_PROFILE");
|
||
g_profile_enabled = (env && *env && *env != '0') ? 1 : 0;
|
||
}
|
||
return g_profile_enabled;
|
||
}
|
||
|
||
// Forward declarations for atexit registration
|
||
void tiny_fast_print_stats(void);
|
||
void tiny_fast_print_profile(void);
|
||
|
||
// ========== Slow Path: Refill from Magazine/SuperSlab ==========
|
||
|
||
void* tiny_fast_refill(int class_idx) {
|
||
uint64_t start = profile_enabled() ? rdtsc() : 0;
|
||
|
||
if (class_idx < 0 || class_idx >= TINY_FAST_CLASS_COUNT) {
|
||
return NULL;
|
||
}
|
||
|
||
g_tiny_fast_refill_count++;
|
||
|
||
// Register stats printer on first refill (once per thread)
|
||
static __thread int stats_registered = 0;
|
||
if (!stats_registered) {
|
||
atexit(tiny_fast_print_stats);
|
||
if (profile_enabled()) {
|
||
atexit(tiny_fast_print_profile);
|
||
}
|
||
stats_registered = 1;
|
||
}
|
||
|
||
// ========================================================================
|
||
// Phase 6-6: Batch Refill Optimization (Phase 3)
|
||
// Inspired by mimalloc's page-based refill and glibc's tcache batch refill
|
||
//
|
||
// OLD: 16 individual allocations + 16 individual pushes (16 × 100 cycles = 1,600 cycles)
|
||
// NEW: Batch allocate + link in one pass (~200 cycles, -87% cost)
|
||
// ========================================================================
|
||
|
||
// Get size from class mapping
|
||
static const size_t class_sizes[] = {16, 24, 32, 40, 48, 56, 64, 80, 96, 112, 128, 144, 160, 176, 192, 256};
|
||
size_t size = (class_idx < 16) ? class_sizes[class_idx] : 16;
|
||
|
||
// Step 1: Batch allocate into temporary array
|
||
void* batch[TINY_FAST_REFILL_BATCH];
|
||
int count = 0;
|
||
|
||
extern void* hak_tiny_alloc(size_t size);
|
||
for (int i = 0; i < TINY_FAST_REFILL_BATCH; i++) {
|
||
void* ptr = hak_tiny_alloc(size);
|
||
if (!ptr) break; // OOM or allocation failed
|
||
batch[count++] = ptr;
|
||
}
|
||
|
||
// Track refill results
|
||
if (count == 0) {
|
||
g_refill_fail_count++;
|
||
return NULL; // Complete failure
|
||
} else if (count < TINY_FAST_REFILL_BATCH) {
|
||
g_refill_partial_count++;
|
||
} else {
|
||
g_refill_success_count++;
|
||
}
|
||
g_refill_total_blocks += count;
|
||
|
||
// Step 2: Link all blocks into freelist in one pass (batch linking)
|
||
// This is the key optimization: N individual pushes → 1 batch link
|
||
for (int i = 0; i < count - 1; i++) {
|
||
*(void**)batch[i] = batch[i + 1];
|
||
}
|
||
*(void**)batch[count - 1] = NULL; // Terminate list
|
||
|
||
// Step 3: Attach batch to cache head
|
||
g_tiny_fast_cache[class_idx] = batch[0];
|
||
g_tiny_fast_count[class_idx] = count;
|
||
|
||
// Step 4: Pop one for the caller
|
||
void* result = g_tiny_fast_cache[class_idx];
|
||
g_tiny_fast_cache[class_idx] = *(void**)result;
|
||
g_tiny_fast_count[class_idx]--;
|
||
|
||
// Profile: Record refill cycles
|
||
if (start) {
|
||
g_tiny_refill_cycles += (rdtsc() - start);
|
||
}
|
||
|
||
return result;
|
||
}
|
||
|
||
// ========== Slow Path: Drain to Magazine/SuperSlab ==========
|
||
|
||
void tiny_fast_drain(int class_idx) {
|
||
if (class_idx < 0 || class_idx >= TINY_FAST_CLASS_COUNT) {
|
||
return;
|
||
}
|
||
|
||
g_tiny_fast_drain_count++;
|
||
|
||
// ========================================================================
|
||
// Phase 6-7: Drain from free_head (Phase 2)
|
||
// Since frees go to free_head, drain from there when capacity exceeded
|
||
// ========================================================================
|
||
|
||
// Drain half of the free_head to Magazine/SuperSlab
|
||
// TODO: For now, we just reduce the count limit
|
||
// In a full implementation, we'd push blocks back to Magazine freelist
|
||
|
||
// Simple approach: just drop half the cache (temporary, for testing)
|
||
// A full implementation would return blocks to SuperSlab freelist
|
||
uint32_t target = TINY_FAST_CACHE_CAP / 2;
|
||
|
||
while (g_tiny_fast_free_count[class_idx] > target) {
|
||
void* ptr = g_tiny_fast_free_head[class_idx];
|
||
if (!ptr) break;
|
||
|
||
g_tiny_fast_free_head[class_idx] = *(void**)ptr;
|
||
g_tiny_fast_free_count[class_idx]--;
|
||
|
||
// TODO: Return to Magazine/SuperSlab
|
||
// For now, we'll just re-push it (no-op, but prevents loss)
|
||
// In production, call hak_tiny_free_slow(ptr, class_idx)
|
||
}
|
||
}
|
||
|
||
// ========== Debug Stats ==========
|
||
|
||
void tiny_fast_print_stats(void) {
|
||
static const char* env = NULL;
|
||
static int checked = 0;
|
||
|
||
if (!checked) {
|
||
env = getenv("HAKMEM_TINY_FAST_STATS");
|
||
checked = 1;
|
||
}
|
||
|
||
if (env && *env && *env != '0') {
|
||
fprintf(stderr, "[TINY_FAST] refills=%lu drains=%lu\n",
|
||
(unsigned long)g_tiny_fast_refill_count,
|
||
(unsigned long)g_tiny_fast_drain_count);
|
||
}
|
||
}
|
||
|
||
// ========== RDTSC Cycle Profiling Output ==========
|
||
|
||
// External routing counters from hakmem.c
|
||
extern __thread uint64_t g_malloc_total_calls;
|
||
extern __thread uint64_t g_malloc_tiny_size_match;
|
||
extern __thread uint64_t g_malloc_fast_path_tried;
|
||
extern __thread uint64_t g_malloc_fast_path_null;
|
||
extern __thread uint64_t g_malloc_slow_path;
|
||
|
||
void tiny_fast_print_profile(void) {
|
||
if (!profile_enabled()) return;
|
||
if (g_tiny_malloc_count == 0 && g_tiny_free_count == 0) return; // No data
|
||
|
||
fprintf(stderr, "\n========== HAKMEM Tiny Fast Path Profile (RDTSC cycles) ==========\n");
|
||
|
||
// Routing statistics first
|
||
if (g_malloc_total_calls > 0) {
|
||
fprintf(stderr, "\n[ROUTING]\n");
|
||
fprintf(stderr, " Total malloc() calls: %lu\n", (unsigned long)g_malloc_total_calls);
|
||
fprintf(stderr, " Size <= %d (tiny range): %lu (%.1f%%)\n",
|
||
TINY_FAST_THRESHOLD,
|
||
(unsigned long)g_malloc_tiny_size_match,
|
||
100.0 * g_malloc_tiny_size_match / g_malloc_total_calls);
|
||
fprintf(stderr, " Fast path tried: %lu (%.1f%%)\n",
|
||
(unsigned long)g_malloc_fast_path_tried,
|
||
100.0 * g_malloc_fast_path_tried / g_malloc_total_calls);
|
||
fprintf(stderr, " Fast path returned NULL: %lu (%.1f%% of tried)\n",
|
||
(unsigned long)g_malloc_fast_path_null,
|
||
g_malloc_fast_path_tried > 0 ? 100.0 * g_malloc_fast_path_null / g_malloc_fast_path_tried : 0);
|
||
fprintf(stderr, " Slow path entered: %lu (%.1f%%)\n\n",
|
||
(unsigned long)g_malloc_slow_path,
|
||
100.0 * g_malloc_slow_path / g_malloc_total_calls);
|
||
}
|
||
|
||
if (g_tiny_malloc_count > 0) {
|
||
uint64_t avg_malloc = g_tiny_malloc_cycles / g_tiny_malloc_count;
|
||
fprintf(stderr, "[MALLOC] count=%lu, total_cycles=%lu, avg_cycles=%lu\n",
|
||
(unsigned long)g_tiny_malloc_count,
|
||
(unsigned long)g_tiny_malloc_cycles,
|
||
(unsigned long)avg_malloc);
|
||
}
|
||
|
||
if (g_tiny_free_count > 0) {
|
||
uint64_t avg_free = g_tiny_free_cycles / g_tiny_free_count;
|
||
fprintf(stderr, "[FREE] count=%lu, total_cycles=%lu, avg_cycles=%lu\n",
|
||
(unsigned long)g_tiny_free_count,
|
||
(unsigned long)g_tiny_free_cycles,
|
||
(unsigned long)avg_free);
|
||
}
|
||
|
||
if (g_tiny_fast_refill_count > 0) {
|
||
uint64_t avg_refill = g_tiny_refill_cycles / g_tiny_fast_refill_count;
|
||
fprintf(stderr, "[REFILL] count=%lu, total_cycles=%lu, avg_cycles=%lu\n",
|
||
(unsigned long)g_tiny_fast_refill_count,
|
||
(unsigned long)g_tiny_refill_cycles,
|
||
(unsigned long)avg_refill);
|
||
|
||
// Refill success/failure breakdown
|
||
fprintf(stderr, "[REFILL SUCCESS] count=%lu (%.1f%%) - full batch\n",
|
||
(unsigned long)g_refill_success_count,
|
||
100.0 * g_refill_success_count / g_tiny_fast_refill_count);
|
||
fprintf(stderr, "[REFILL PARTIAL] count=%lu (%.1f%%) - some blocks\n",
|
||
(unsigned long)g_refill_partial_count,
|
||
100.0 * g_refill_partial_count / g_tiny_fast_refill_count);
|
||
fprintf(stderr, "[REFILL FAIL] count=%lu (%.1f%%) - zero blocks\n",
|
||
(unsigned long)g_refill_fail_count,
|
||
100.0 * g_refill_fail_count / g_tiny_fast_refill_count);
|
||
fprintf(stderr, "[REFILL AVG BLOCKS] %.1f per refill (target=%d)\n",
|
||
(double)g_refill_total_blocks / g_tiny_fast_refill_count,
|
||
TINY_FAST_REFILL_BATCH);
|
||
}
|
||
|
||
if (g_tiny_migration_count > 0) {
|
||
uint64_t avg_migration = g_tiny_migration_cycles / g_tiny_migration_count;
|
||
fprintf(stderr, "[MIGRATE] count=%lu, total_cycles=%lu, avg_cycles=%lu\n",
|
||
(unsigned long)g_tiny_migration_count,
|
||
(unsigned long)g_tiny_migration_cycles,
|
||
(unsigned long)avg_migration);
|
||
}
|
||
|
||
fprintf(stderr, "===================================================================\n\n");
|
||
}
|