52386401b3
Major Features: - Debug counter infrastructure for Refill Stage tracking - Free Pipeline counters (ss_local, ss_remote, tls_sll) - Diagnostic counters for early return analysis - Unified larson.sh benchmark runner with profiles - Phase 6-3 regression analysis documentation Bug Fixes: - Fix SuperSlab disabled by default (HAKMEM_TINY_USE_SUPERSLAB) - Fix profile variable naming consistency - Add .gitignore patterns for large files Performance: - Phase 6-3: 4.79 M ops/s (has OOM risk) - With SuperSlab: 3.13 M ops/s (+19% improvement) This is a clean repository without large log files. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
53 lines
1.8 KiB
C
53 lines
1.8 KiB
C
#ifndef TINY_DEBUG_H
|
|
#define TINY_DEBUG_H
|
|
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <stdatomic.h>
|
|
#include "hakmem_tiny_superslab.h"
|
|
#include "hakmem_tiny.h"
|
|
|
|
static inline int tiny_alloc_debug_enabled(void) {
|
|
static int g_debug = -1;
|
|
if (__builtin_expect(g_debug == -1, 0)) {
|
|
const char* e = getenv("HAKMEM_TINY_ALLOC_DEBUG");
|
|
g_debug = (e && atoi(e) != 0) ? 1 : 0;
|
|
}
|
|
return g_debug;
|
|
}
|
|
|
|
static inline void tiny_alloc_dump_tls_state(int class_idx, const char* tag, TinyTLSSlab* tls) {
|
|
if (!tiny_alloc_debug_enabled()) return;
|
|
fprintf(stderr,
|
|
"[ALLOC-DBG:%s] class=%d tls_ss=%p slab_idx=%u meta=%p slab_base=%p\n",
|
|
tag ? tag : "?", class_idx,
|
|
(void*)tls->ss, (unsigned)tls->slab_idx,
|
|
(void*)tls->meta, (void*)tls->slab_base);
|
|
SuperSlab* ss = tls->ss;
|
|
if (!(ss && ss->magic == SUPERSLAB_MAGIC)) {
|
|
fprintf(stderr,
|
|
" tls_ss invalid: ss=%p magic=0x%llx\n",
|
|
(void*)ss,
|
|
ss ? (unsigned long long)ss->magic : 0ull);
|
|
return;
|
|
}
|
|
int cap = ss_slabs_capacity(ss);
|
|
fprintf(stderr,
|
|
" ss active_slabs=%u cap=%d bitmap=0x%08x total_active=%u ref=%u\n",
|
|
ss->active_slabs, cap, ss->slab_bitmap,
|
|
atomic_load_explicit(&ss->total_active_blocks, memory_order_relaxed),
|
|
atomic_load_explicit(&ss->refcount, memory_order_relaxed));
|
|
int limit = (cap < 6) ? cap : 6;
|
|
for (int i = 0; i < limit; i++) {
|
|
uint32_t mask = 1u << i;
|
|
TinySlabMeta* meta = &ss->slabs[i];
|
|
fprintf(stderr,
|
|
" slab%02d active=%d used=%u cap=%u freelist=%p owner=%u\n",
|
|
i, (ss->slab_bitmap & mask) ? 1 : 0,
|
|
(unsigned)meta->used, (unsigned)meta->capacity,
|
|
meta->freelist, meta->owner_tid);
|
|
}
|
|
}
|
|
|
|
#endif // TINY_DEBUG_H
|