1b196b3ac0
Phase 4-2: - Add TinyC6UltraFreeTLS structure with 128-slot TLS freelist - Implement tiny_c6_ultra_free_fast/slow for C6 free hot path - Add c6_ultra_free_fast counter to FreePathStats - ENV gate: HAKMEM_TINY_C6_ULTRA_FREE_ENABLED (default: OFF) Phase 4-3: - Add segment learning on first C6 free via ss_fast_lookup() - Learn seg_base/seg_end from SuperSlab for range check - Increase cache capacity from 32 to 128 blocks Results: - Segment learning works: fast path captures blocks in segment - However, without alloc integration, cache fills up and overflows to legacy - Net effect: +1-3% (within noise range) - Drain strategy also tested: no benefit (equal overhead) Conclusion: - Free-only TLS cache is limited without alloc-side integration - Core v6 already has alloc/free integrated TLS (but -12% slower) - Keep as research box (ENV default OFF) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
44 lines
1.6 KiB
C
44 lines
1.6 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 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.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);
|
|
}
|