62 lines
2.3 KiB
C
62 lines
2.3 KiB
C
|
// ss_hot_prewarm_box.h - Box SS-HotPrewarm
|
||
|
|
// Phase 20-1: Aggressive TLS SLL + SuperSlab prewarming for page fault reduction
|
||
|
|
//
|
||
|
|
// Purpose:
|
||
|
|
// - Pre-warm TLS SLL cache with ENV-controlled per-class targets
|
||
|
|
// - Reduce page faults by allocating and populating SuperSlabs upfront
|
||
|
|
// - Target: 50-66% page fault reduction → +20-40% performance
|
||
|
|
//
|
||
|
|
// Design:
|
||
|
|
// - ENV controls: HAKMEM_TINY_PREWARM_C2, _C3, _C4, _C5
|
||
|
|
// - Default aggressive targets: C2/C3=128, C4/C5=64 (ChatGPT strategy)
|
||
|
|
// - Uses Box Prewarm API (box_prewarm_tls) for safe TLS SLL warming
|
||
|
|
// - Automatically triggers SuperSlab allocation + populate
|
||
|
|
//
|
||
|
|
// ENV Variables:
|
||
|
|
// HAKMEM_TINY_PREWARM_C2=N - Prewarm C2 (33-64B) with N blocks [DEFAULT: 128]
|
||
|
|
// HAKMEM_TINY_PREWARM_C3=N - Prewarm C3 (65-128B) with N blocks [DEFAULT: 128]
|
||
|
|
// HAKMEM_TINY_PREWARM_C4=N - Prewarm C4 (129-256B) with N blocks [DEFAULT: 64]
|
||
|
|
// HAKMEM_TINY_PREWARM_C5=N - Prewarm C5 (257-512B) with N blocks [DEFAULT: 64]
|
||
|
|
// HAKMEM_TINY_PREWARM_ALL=N - Override all classes with N blocks [DEFAULT: OFF]
|
||
|
|
//
|
||
|
|
// Example:
|
||
|
|
// export HAKMEM_TINY_PREWARM_C2=256
|
||
|
|
// export HAKMEM_TINY_PREWARM_C3=256
|
||
|
|
// ./bench_random_mixed_hakmem
|
||
|
|
|
||
|
|
#ifndef HAK_BOX_SS_HOT_PREWARM_H
|
||
|
|
#define HAK_BOX_SS_HOT_PREWARM_H
|
||
|
|
|
||
|
|
#include <stdint.h>
|
||
|
|
#include <stdbool.h>
|
||
|
|
|
||
|
|
// ============================================================================
|
||
|
|
// Box SS-HotPrewarm API
|
||
|
|
// ============================================================================
|
||
|
|
|
||
|
|
// Pre-warm TLS SLL caches for all Tiny classes based on ENV settings
|
||
|
|
//
|
||
|
|
// What it does:
|
||
|
|
// 1. Read ENV variables (HAKMEM_TINY_PREWARM_C2, etc.)
|
||
|
|
// 2. For each class with non-zero target:
|
||
|
|
// - Call box_prewarm_tls(class_idx, target)
|
||
|
|
// - This allocates SuperSlab + populates pages + fills TLS SLL
|
||
|
|
// 3. Report total blocks pre-warmed
|
||
|
|
//
|
||
|
|
// Returns: total blocks pre-warmed across all classes
|
||
|
|
//
|
||
|
|
// Thread-safe: uses TLS, call from init only
|
||
|
|
// Idempotent: safe to call multiple times (subsequent calls are no-op)
|
||
|
|
//
|
||
|
|
// Expected impact:
|
||
|
|
// - Page faults: -50-66% (amortized upfront)
|
||
|
|
// - Performance: +20-40% (per ChatGPT Phase 20 strategy)
|
||
|
|
//
|
||
|
|
int box_ss_hot_prewarm_all(void);
|
||
|
|
|
||
|
|
// Get prewarm target for a specific class (after ENV parsing)
|
||
|
|
// Returns: target count, or 0 if no prewarm needed
|
||
|
|
int box_ss_hot_prewarm_target(int class_idx);
|
||
|
|
|
||
|
|
#endif // HAK_BOX_SS_HOT_PREWARM_H
|