Added compile-time guards (#if HAKMEM_BUILD_RELEASE) to eliminate DEBUG ENV variable overhead in RELEASE builds. Variables guarded (14 total): - HAKMEM_TINY_TRACE_RING, HAKMEM_TINY_DUMP_RING_ATEXIT - HAKMEM_TINY_RF_TRACE, HAKMEM_TINY_MAILBOX_TRACE - HAKMEM_TINY_MAILBOX_TRACE_LIMIT, HAKMEM_TINY_MAILBOX_SLOWDISC - HAKMEM_TINY_MAILBOX_SLOWDISC_PERIOD - HAKMEM_SS_PREWARM_DEBUG, HAKMEM_SS_FREE_DEBUG - HAKMEM_TINY_FRONT_METRICS, HAKMEM_TINY_FRONT_DUMP - HAKMEM_TINY_COUNTERS_DUMP, HAKMEM_TINY_REFILL_DUMP - HAKMEM_PTR_TRACE_DUMP, HAKMEM_PTR_TRACE_VERBOSE Files modified (9 core files): - core/tiny_debug_ring.c (ring trace/dump) - core/box/mailbox_box.c (mailbox trace + slowdisc) - core/tiny_refill.h (refill trace) - core/hakmem_tiny_superslab.c (superslab debug) - core/box/ss_allocation_box.c (allocation debug) - core/tiny_superslab_free.inc.h (free debug) - core/box/front_metrics_box.c (frontend metrics) - core/hakmem_tiny_stats.c (stats dump) - core/ptr_trace.h (pointer trace) Bug fixes during implementation: 1. mailbox_box.c - Fixed variable scope (moved 'used' outside guard) 2. hakmem_tiny_stats.c - Fixed incomplete declarations (on1, on2) Impact: - Binary size: -85KB total - bench_random_mixed_hakmem: 319K → 305K (-14K, -4.4%) - larson_hakmem: 380K → 309K (-71K, -18.7%) - Performance: No regression (16.9-17.9M ops/s maintained) - Functional: All tests pass (Random Mixed + Larson) - Behavior: DEBUG ENV vars correctly ignored in RELEASE builds Testing: - Build: Clean compilation (warnings only, pre-existing) - 100K Random Mixed: 16.9-17.9M ops/s (PASS) - 10K Larson: 25.9M ops/s (PASS) - DEBUG ENV verification: Correctly ignored (PASS) Result: 14 DEBUG ENV variables now have zero overhead in RELEASE builds. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
128 lines
5.1 KiB
C
128 lines
5.1 KiB
C
// front_metrics_box.c - Box FrontMetrics Implementation
|
|
// Purpose: Collect and report frontend layer hit rates
|
|
|
|
#include "front_metrics_box.h"
|
|
#include "../hakmem_tiny_stats_api.h"
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
|
|
// ============================================================================
|
|
// Per-thread counters (NEW - declared in header, defined here)
|
|
// ============================================================================
|
|
|
|
__thread uint64_t g_front_ultrahot_hit[TINY_NUM_CLASSES] = {0};
|
|
__thread uint64_t g_front_ultrahot_miss[TINY_NUM_CLASSES] = {0};
|
|
|
|
__thread uint64_t g_front_heapv2_hit[TINY_NUM_CLASSES] = {0};
|
|
__thread uint64_t g_front_heapv2_miss[TINY_NUM_CLASSES] = {0};
|
|
|
|
__thread uint64_t g_front_class5_hit[TINY_NUM_CLASSES] = {0};
|
|
__thread uint64_t g_front_class5_miss[TINY_NUM_CLASSES] = {0};
|
|
|
|
// ============================================================================
|
|
// Existing counters (defined in hakmem_tiny.c, extern here for reading)
|
|
// ============================================================================
|
|
|
|
extern unsigned long long g_front_fc_hit[TINY_NUM_CLASSES];
|
|
extern unsigned long long g_front_fc_miss[TINY_NUM_CLASSES];
|
|
extern unsigned long long g_front_sfc_hit[TINY_NUM_CLASSES];
|
|
extern unsigned long long g_front_sll_hit[TINY_NUM_CLASSES];
|
|
|
|
// ============================================================================
|
|
// Enable flag (cached)
|
|
// ============================================================================
|
|
|
|
int front_metrics_enabled(void) {
|
|
static int g_enabled = -1;
|
|
if (__builtin_expect(g_enabled == -1, 0)) {
|
|
#if HAKMEM_BUILD_RELEASE
|
|
g_enabled = 0;
|
|
#else
|
|
const char* env = getenv("HAKMEM_TINY_FRONT_METRICS");
|
|
g_enabled = (env && *env && *env != '0') ? 1 : 0;
|
|
#endif
|
|
}
|
|
return g_enabled;
|
|
}
|
|
|
|
// ============================================================================
|
|
// Dump frontend metrics (CSV format)
|
|
// ============================================================================
|
|
|
|
void hak_tiny_front_metrics_dump(void) {
|
|
if (!front_metrics_enabled()) {
|
|
return;
|
|
}
|
|
|
|
const char* dump_env =
|
|
#if HAKMEM_BUILD_RELEASE
|
|
NULL;
|
|
if (1) { return; }
|
|
#else
|
|
getenv("HAKMEM_TINY_FRONT_DUMP");
|
|
if (!(dump_env && *dump_env && *dump_env != '0')) {
|
|
return;
|
|
}
|
|
#endif
|
|
|
|
fprintf(stderr, "\n========== Box FrontMetrics: Layer Hit Rates ==========\n");
|
|
fprintf(stderr, "Purpose: Identify which frontend layers are doing real work\n");
|
|
fprintf(stderr, "Legend: UH=UltraHot, HV2=HeapV2, C5=Class5, FC=FastCache, SFC=SuperFrontCache, SLL=TLS_SLL\n\n");
|
|
|
|
fprintf(stderr, "%-5s %10s %10s %10s %10s %10s %10s %12s | %6s %6s %6s %6s %6s %6s\n",
|
|
"Class", "UH_hit", "HV2_hit", "C5_hit", "FC_hit", "SFC_hit", "SLL_hit", "Total",
|
|
"UH%", "HV2%", "C5%", "FC%", "SFC%", "SLL%");
|
|
fprintf(stderr, "------|----------|----------|----------|----------|----------|----------|-------------|");
|
|
fprintf(stderr, "-------|-------|-------|-------|-------|-------\n");
|
|
|
|
for (int cls = 0; cls < TINY_NUM_CLASSES; cls++) {
|
|
uint64_t uh_hit = g_front_ultrahot_hit[cls];
|
|
uint64_t hv2_hit = g_front_heapv2_hit[cls];
|
|
uint64_t c5_hit = g_front_class5_hit[cls];
|
|
uint64_t fc_hit = g_front_fc_hit[cls];
|
|
uint64_t sfc_hit = g_front_sfc_hit[cls];
|
|
uint64_t sll_hit = g_front_sll_hit[cls];
|
|
|
|
uint64_t total = uh_hit + hv2_hit + c5_hit + fc_hit + sfc_hit + sll_hit;
|
|
|
|
if (total == 0) {
|
|
fprintf(stderr, "C%-4d %10s %10s %10s %10s %10s %10s %12s | %6s %6s %6s %6s %6s %6s\n",
|
|
cls, "-", "-", "-", "-", "-", "-", "-", "-", "-", "-", "-", "-", "-");
|
|
continue;
|
|
}
|
|
|
|
double uh_pct = (double)uh_hit / total * 100.0;
|
|
double hv2_pct = (double)hv2_hit / total * 100.0;
|
|
double c5_pct = (double)c5_hit / total * 100.0;
|
|
double fc_pct = (double)fc_hit / total * 100.0;
|
|
double sfc_pct = (double)sfc_hit / total * 100.0;
|
|
double sll_pct = (double)sll_hit / total * 100.0;
|
|
|
|
fprintf(stderr, "C%-4d %10lu %10lu %10lu %10lu %10lu %10lu %12lu | %5.1f%% %5.1f%% %5.1f%% %5.1f%% %5.1f%% %5.1f%%\n",
|
|
cls,
|
|
(unsigned long)uh_hit,
|
|
(unsigned long)hv2_hit,
|
|
(unsigned long)c5_hit,
|
|
(unsigned long)fc_hit,
|
|
(unsigned long)sfc_hit,
|
|
(unsigned long)sll_hit,
|
|
(unsigned long)total,
|
|
uh_pct, hv2_pct, c5_pct, fc_pct, sfc_pct, sll_pct);
|
|
}
|
|
|
|
fprintf(stderr, "=======================================================\n\n");
|
|
|
|
// Analysis recommendations
|
|
fprintf(stderr, "Analysis Recommendations:\n");
|
|
fprintf(stderr, " - Layers with >80%% hit rate: Keep and optimize (hot path)\n");
|
|
fprintf(stderr, " - Layers with <5%% hit rate: Consider pruning (dead weight)\n");
|
|
fprintf(stderr, " - Multiple layers >20%%: Potential redundancy, test pruning\n\n");
|
|
}
|
|
|
|
// Register dump at shutdown
|
|
static void front_metrics_atexit(void) __attribute__((destructor));
|
|
static void front_metrics_atexit(void) {
|
|
hak_tiny_front_metrics_dump();
|
|
}
|