9830eff6cc
Parasitic TLS cache: alloc now pops from the TLS freelist filled by free. Implementation: - malloc_tiny_fast(): C6 class-specific TLS pop check before route switch - if (class_idx == 6 && tiny_c6_ultra_free_enabled()) - pop from TinyC6UltraFreeTLS.freelist[--count] - return USER pointer (BASE + 1) - FreePathStats: Added c6_ultra_alloc_hit counter for observability Results (Mixed 16-1024B): - OFF: 40.2M ops/s baseline - ON: 42.2M ops/s (+4.9%) stable Per-profile: - Mixed: +4.9% (40.2M → 42.2M) - C6-heavy: +7.6% (40.7M → 43.8M) Free-alloc loop: - free: TLS push (all C6 frees) - alloc: TLS pop (all C6 allocs in steady state) - Cache never fills, no legacy overflow - C6 legacy_by_class reduced from 137K to 0 (100% elimination) Key insight: - Free-only TLS cache fails without alloc integration - Once integrated, creates perfect load-balancing loop - Alloc drains exactly what free fills 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
45 lines
1.7 KiB
C
45 lines
1.7 KiB
C
#include "free_path_stats_box.h"
|
|
#include <stdio.h>
|
|
|
|
FreePathStats g_free_path_stats = {0};
|
|
|
|
// Helper function for pool_api.inc.h (to avoid inline include issues)
|
|
void free_path_stat_inc_pool_v1_fast(void) {
|
|
if (__builtin_expect(free_path_stats_enabled(), 0)) {
|
|
g_free_path_stats.pool_v1_fast++;
|
|
}
|
|
}
|
|
|
|
__attribute__((destructor))
|
|
static void free_path_stats_dump(void) {
|
|
if (!free_path_stats_enabled()) {
|
|
return;
|
|
}
|
|
|
|
fprintf(stderr, "[FREE_PATH_STATS] total=%lu c7_ultra=%lu c6_ultra_free=%lu c6_ultra_alloc=%lu small_v3=%lu v6=%lu tiny_v1=%lu pool_v1=%lu remote=%lu super_lookup=%lu legacy_fb=%lu\n",
|
|
g_free_path_stats.total_calls,
|
|
g_free_path_stats.c7_ultra_fast,
|
|
g_free_path_stats.c6_ultra_free_fast, // Phase 4-2
|
|
g_free_path_stats.c6_ultra_alloc_hit, // Phase 4-4
|
|
g_free_path_stats.smallheap_v3_fast,
|
|
g_free_path_stats.smallheap_v6_fast,
|
|
g_free_path_stats.tiny_heap_v1_fast,
|
|
g_free_path_stats.pool_v1_fast,
|
|
g_free_path_stats.remote_free,
|
|
g_free_path_stats.super_lookup_called,
|
|
g_free_path_stats.legacy_fallback);
|
|
|
|
// Phase 4-1: Legacy per-class breakdown
|
|
fprintf(stderr, "[FREE_PATH_STATS_LEGACY_BY_CLASS] c0=%lu c1=%lu c2=%lu c3=%lu c4=%lu c5=%lu c6=%lu c7=%lu\n",
|
|
g_free_path_stats.legacy_by_class[0],
|
|
g_free_path_stats.legacy_by_class[1],
|
|
g_free_path_stats.legacy_by_class[2],
|
|
g_free_path_stats.legacy_by_class[3],
|
|
g_free_path_stats.legacy_by_class[4],
|
|
g_free_path_stats.legacy_by_class[5],
|
|
g_free_path_stats.legacy_by_class[6],
|
|
g_free_path_stats.legacy_by_class[7]);
|
|
|
|
fflush(stderr);
|
|
}
|