Summary - Fix SEGV root cause in Tiny random_mixed: TINY_REMOTE_SENTINEL leaked from Remote queue into freelist/TLS SLL. - Clear/guard sentinel at the single boundary where Remote merges to freelist. - Add minimal defense-in-depth in freelist_pop and TLS SLL pop. - Silence verbose prints behind debug gates to reduce noise in release runs. - Pool TLS: integrate Remote Queue drain at refill boundary to avoid unnecessary backend carve/OS calls when possible. - DX: strengthen build.sh with help/list/verify and add docs/BUILDING_QUICKSTART.md. Details - core/superslab/superslab_inline.h: guard head/node against TINY_REMOTE_SENTINEL; sanitize node[0] when splicing local chain; only print diagnostics when debug guard is enabled. - core/slab_handle.h: freelist_pop breaks on sentinel head (fail-fast under strict). - core/tiny_alloc_fast_inline.h: TLS SLL pop breaks on sentinel head (rare branch). - core/tiny_superslab_free.inc.h: sentinel scan log behind debug guard. - core/pool_refill.c: try pool_remote_pop_chain() before backend carve in pool_refill_and_alloc(). - core/tiny_adaptive_sizing.c: default adaptive logs off; enable via HAKMEM_ADAPTIVE_LOG=1. - build.sh: add help/list/verify; EXTRA_MAKEFLAGS passthrough; echo pinned flags. - docs/BUILDING_QUICKSTART.md: add one‑pager for targets/flags/env/perf/strace. Verification (high level) - Tiny random_mixed 10k 256/1024: SEGV resolved; runs complete. - Pool TLS 1T/4T perf: HAKMEM >= system (≈ +0.7% 1T, ≈ +2.9% 4T); syscall counts ~10–13. Known issues (to address next) - Tiny random_mixed perf is weak vs system: - 1T/500k/256: cycles/op ≈ 240 vs ~47 (≈5× slower), IPC ≈0.92, branch‑miss ≈11%. - 1T/500k/1024: cycles/op ≈ 149 vs ~53 (≈2.8× slower), IPC ≈0.82, branch‑miss ≈10.5%. - Hypothesis: frequent SuperSlab path for class7 (fast_cap=0), branchy refill/adopt, and hot-path divergence. - Proposed next steps: - Introduce fast_cap>0 for class7 (bounded TLS SLL) and a simpler batch refill. - Add env‑gated Remote Side OFF for 1T A/B (reduce side-table and guards). - Revisit likely/unlikely and unify adopt boundary sequencing (drain→bind→acquire) for Tiny.
99 lines
2.5 KiB
C
99 lines
2.5 KiB
C
#include "pool_refill.h"
|
|
#include "pool_tls.h"
|
|
#include "pool_tls_arena.h"
|
|
#include "pool_tls_remote.h"
|
|
#include <sys/mman.h>
|
|
#include <stdint.h>
|
|
#include <errno.h>
|
|
|
|
// Get refill count from Box 1
|
|
extern int pool_get_refill_count(int class_idx);
|
|
|
|
// Refill and return first block
|
|
void* pool_refill_and_alloc(int class_idx) {
|
|
int count = pool_get_refill_count(class_idx);
|
|
if (count <= 0) return NULL;
|
|
|
|
// Refill boundary integration: try draining remote frees first.
|
|
// If we can satisfy from remote queue, avoid backend carve (OS pressure).
|
|
{
|
|
void* rchain = NULL;
|
|
int rgot = pool_remote_pop_chain(class_idx, count, &rchain);
|
|
if (rgot > 0 && rchain) {
|
|
// Pop one to return, install the rest into TLS
|
|
void* ret = rchain;
|
|
rchain = *(void**)rchain;
|
|
rgot--;
|
|
if (rgot > 0 && rchain) {
|
|
pool_install_chain(class_idx, rchain, rgot);
|
|
}
|
|
#if POOL_USE_HEADERS
|
|
*((uint8_t*)ret - POOL_HEADER_SIZE) = POOL_MAGIC | class_idx;
|
|
#endif
|
|
return ret;
|
|
}
|
|
}
|
|
|
|
// Batch allocate from existing Pool backend
|
|
void* chain = backend_batch_carve(class_idx, count);
|
|
if (!chain) return NULL; // OOM
|
|
|
|
// Pop first block for return
|
|
void* ret = chain;
|
|
chain = *(void**)chain;
|
|
count--;
|
|
|
|
#if POOL_USE_HEADERS
|
|
// Write header for the block we're returning
|
|
*((uint8_t*)ret - POOL_HEADER_SIZE) = POOL_MAGIC | class_idx;
|
|
#endif
|
|
|
|
// Install rest in TLS (if any)
|
|
if (count > 0 && chain) {
|
|
pool_install_chain(class_idx, chain, count);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
// Backend batch carve - Phase 1.5a: TLS Arena with chunk carving
|
|
void* backend_batch_carve(int class_idx, int count) {
|
|
if (class_idx < 0 || class_idx >= POOL_SIZE_CLASSES || count <= 0) {
|
|
return NULL;
|
|
}
|
|
|
|
// Allocate blocks array on stack
|
|
void* blocks[64]; // Max refill count is 64
|
|
if (count > 64) count = 64;
|
|
|
|
// Carve from TLS Arena (Phase 1.5a)
|
|
int carved = arena_batch_carve(class_idx, blocks, count);
|
|
if (carved == 0) {
|
|
return NULL; // OOM
|
|
}
|
|
|
|
// Chain the carved blocks
|
|
void* head = NULL;
|
|
void* tail = NULL;
|
|
|
|
for (int i = 0; i < carved; i++) {
|
|
void* block = blocks[i];
|
|
|
|
// Chain the block
|
|
if (!head) {
|
|
head = block;
|
|
tail = block;
|
|
} else {
|
|
*(void**)tail = block;
|
|
tail = block;
|
|
}
|
|
}
|
|
|
|
// Terminate chain
|
|
if (tail) {
|
|
*(void**)tail = NULL;
|
|
}
|
|
|
|
return head;
|
|
}
|