984cca41ef
Performance Results: - Throughput: 2.66M ops/s → 3.8M ops/s (+43% improvement) - sp_meta_find_or_create: O(N) linear scan → O(1) direct pointer - Stage 2 metadata scan: 100% → 10-20% (80-90% reduction via hints) Core Optimizations: 1. O(1) Metadata Lookup (superslab_types.h) - Added `shared_meta` pointer field to SuperSlab struct - Eliminates O(N) linear search through ss_metadata[] array - First access: O(N) scan + cache | Subsequent: O(1) direct return 2. sp_meta_find_or_create Fast Path (hakmem_shared_pool.c) - Check cached ss->shared_meta first before linear scan - Cache pointer after successful linear scan for future lookups - Reduces 7.8% CPU hotspot to near-zero for hot paths 3. Stage 2 Class Hints Fast Path (hakmem_shared_pool_acquire.c) - Try class_hints[class_idx] FIRST before full metadata scan - Uses O(1) ss->shared_meta lookup for hint validation - __builtin_expect() for branch prediction optimization - 80-90% of acquire calls now skip full metadata scan 4. Proper Initialization (ss_allocation_box.c) - Initialize shared_meta = NULL in superslab_allocate() - Ensures correct NULL-check semantics for new SuperSlabs Additional Improvements: - Updated ptr_trace and debug ring for release build efficiency - Enhanced ENV variable documentation and analysis - Added learner_env_box.h for configuration management - Various Box optimizations for reduced overhead Thread Safety: - All atomic operations use correct memory ordering - shared_meta cached under mutex protection - Lock-free Stage 2 uses proper CAS with acquire/release semantics Testing: - Benchmark: 1M iterations, 3.8M ops/s stable - Build: Clean compile RELEASE=0 and RELEASE=1 - No crashes, memory leaks, or correctness issues Next Optimization Candidates: - P1: Per-SuperSlab free slot bitmap for O(1) slot claiming - P2: Reduce Stage 2 critical section size - P3: Page pre-faulting (MAP_POPULATE) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
84 lines
2.6 KiB
C
84 lines
2.6 KiB
C
// pagefault_telemetry_box.c - Box PageFaultTelemetry implementation
|
|
|
|
#include "pagefault_telemetry_box.h"
|
|
|
|
#include "../hakmem_tiny_stats_api.h" // For macros / flags
|
|
#include "../hakmem_stats_master.h" // Phase 4d: Master stats control
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
|
|
// Per-thread state
|
|
__thread uint64_t g_pf_bloom[PF_BUCKET_MAX][16] = {{0}};
|
|
__thread uint64_t g_pf_touch[PF_BUCKET_MAX] = {0};
|
|
|
|
// Enable flag (cached)
|
|
int pagefault_telemetry_enabled(void) {
|
|
static int g_enabled = -1;
|
|
if (__builtin_expect(g_enabled == -1, 0)) {
|
|
const char* env = getenv("HAKMEM_TINY_PAGEFAULT_TELEMETRY");
|
|
g_enabled = (env && *env && *env != '0') ? 1 : 0;
|
|
}
|
|
return g_enabled;
|
|
}
|
|
|
|
// Dump helper
|
|
void pagefault_telemetry_dump(void) {
|
|
if (!pagefault_telemetry_enabled()) {
|
|
return;
|
|
}
|
|
|
|
if (!hak_stats_check("HAKMEM_TINY_PAGEFAULT_DUMP", "pagefault")) {
|
|
return;
|
|
}
|
|
|
|
fprintf(stderr, "\n========== Box PageFaultTelemetry: Tiny Page Touch Stats ==========\n");
|
|
fprintf(stderr, "Note: pages ~= popcount(1024-bit bloom); collisions → 下限近似値\n\n");
|
|
fprintf(stderr, "%-5s %12s %12s %12s\n", "Bucket", "touches", "approx_pages", "touches/page");
|
|
fprintf(stderr, "------|------------|------------|------------\n");
|
|
|
|
for (int b = 0; b < PF_BUCKET_MAX; b++) {
|
|
uint64_t touches = g_pf_touch[b];
|
|
if (touches == 0) {
|
|
continue;
|
|
}
|
|
|
|
uint64_t bits = 0;
|
|
for (int w = 0; w < 16; w++) {
|
|
bits += (uint64_t)__builtin_popcountll(g_pf_bloom[b][w]);
|
|
}
|
|
|
|
double pages = (double)bits;
|
|
double tpp = pages > 0.0 ? (double)touches / pages : 0.0;
|
|
|
|
const char* name = NULL;
|
|
char buf[8];
|
|
if (b < PF_BUCKET_TINY_LIMIT) {
|
|
snprintf(buf, sizeof(buf), "C%d", b);
|
|
name = buf;
|
|
} else if (b == PF_BUCKET_MID) {
|
|
name = "MID";
|
|
} else if (b == PF_BUCKET_L25) {
|
|
name = "L25";
|
|
} else if (b == PF_BUCKET_SS_META) {
|
|
name = "SSM";
|
|
} else {
|
|
snprintf(buf, sizeof(buf), "X%d", b);
|
|
name = buf;
|
|
}
|
|
|
|
fprintf(stderr, "%-5s %12llu %12llu %12.1f\n",
|
|
name,
|
|
(unsigned long long)touches,
|
|
(unsigned long long)bits,
|
|
tpp);
|
|
}
|
|
|
|
fprintf(stderr, "===============================================================\n\n");
|
|
}
|
|
|
|
// Auto-dump at thread exit (bench系で 1 回だけ実行される想定)
|
|
static void pagefault_telemetry_atexit(void) __attribute__((destructor));
|
|
static void pagefault_telemetry_atexit(void) {
|
|
pagefault_telemetry_dump();
|
|
}
|