Files
hakmem/core/box/hakmem_env_snapshot_box.c
Moe Charm (CI) 21e2e4ac2b Phase 4 E3-4: ENV Constructor Init (+4.75% GO)
Target: Eliminate E1 lazy init check overhead (3.22% self%)
- E1 consolidated ENV gates but lazy check remained in hot path
- Strategy: __attribute__((constructor(101))) for pre-main init

Implementation:
- ENV gate: HAKMEM_ENV_SNAPSHOT_CTOR=0/1 (default 0, research box)
- core/box/hakmem_env_snapshot_box.c: Constructor function added
  - Reads ENV before main() when CTOR=1
  - Refresh also syncs gate state for bench_profile putenv
- core/box/hakmem_env_snapshot_box.h: Dual-mode enabled check
  - CTOR=1 fast path: direct global read (no lazy branch)
  - CTOR=0 fallback: legacy lazy init (rollback safe)
  - Branch hints adjusted for default OFF baseline

A/B Test Results (Mixed, 10-run, 20M iters, E1=1):
- Baseline (CTOR=0): 44.28M ops/s (mean), 44.60M ops/s (median)
- Optimized (CTOR=1): 46.38M ops/s (mean), 46.53M ops/s (median)
- Improvement: +4.75% mean, +4.35% median

Decision: GO (+4.75% >> +0.5% threshold)
- Expected +0.5-1.5%, achieved +4.75%
- Lazy init branch overhead was larger than expected
- Action: Keep as research box (default OFF), evaluate promotion

Phase 4 Cumulative:
- E1 (ENV Snapshot): +3.92%
- E2 (Alloc Per-Class): -0.21% (NEUTRAL, frozen)
- E3-4 (Constructor Init): +4.75%
- Total Phase 4: ~+8.5%

Deliverables:
- docs/analysis/PHASE4_E3_ENV_CONSTRUCTOR_INIT_DESIGN.md
- docs/analysis/PHASE4_E3_ENV_CONSTRUCTOR_INIT_NEXT_INSTRUCTIONS.md
- docs/analysis/PHASE4_COMPREHENSIVE_STATUS_ANALYSIS.md
- docs/analysis/PHASE4_EXECUTIVE_SUMMARY.md
- scripts/verify_health_profiles.sh (sanity check script)
- CURRENT_TASK.md (E3-4 complete, next instructions)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2025-12-14 02:57:35 +09:00

113 lines
4.3 KiB
C

// hakmem_env_snapshot_box.c - Phase 4 E1: ENV Snapshot Consolidation (implementation)
//
// E3-4 Extension: Constructor init to eliminate lazy check overhead (3.22% self%)
#include "hakmem_env_snapshot_box.h"
#include <stdio.h>
#include <stdlib.h>
#include <stdbool.h>
#include "../hakmem_build_flags.h"
// Forward declare learner check (to avoid circular deps)
extern bool small_learner_v2_enabled(void);
// Global snapshot state (TLS for thread safety)
HakmemEnvSnapshot g_hakmem_env_snapshot = {0};
int g_hakmem_env_snapshot_ready = 0;
// E3-4: Global gate state (not static local - avoids lazy init overhead)
int g_hakmem_env_snapshot_gate = -1;
int g_hakmem_env_snapshot_ctor_mode = -1;
// E3-4: Constructor - run before main() to init gate without lazy check
__attribute__((constructor(101)))
static void hakmem_env_snapshot_gate_ctor(void) {
// Read HAKMEM_ENV_SNAPSHOT_CTOR (default OFF for safety)
const char* ctor_env = getenv("HAKMEM_ENV_SNAPSHOT_CTOR");
g_hakmem_env_snapshot_ctor_mode = (ctor_env && *ctor_env == '1') ? 1 : 0;
if (g_hakmem_env_snapshot_ctor_mode) {
// Constructor mode: init gate now (before any malloc/free calls)
const char* e = getenv("HAKMEM_ENV_SNAPSHOT");
g_hakmem_env_snapshot_gate = (e && *e == '1') ? 1 : 0;
#if !HAKMEM_BUILD_RELEASE
fprintf(stderr, "[E3-4] Constructor init: HAKMEM_ENV_SNAPSHOT_GATE=%d\n",
g_hakmem_env_snapshot_gate);
fflush(stderr);
#endif
}
}
// Internal helper: read all ENV vars and compute effective values
static void hakmem_env_snapshot_load(HakmemEnvSnapshot* snap) {
// Read HAKMEM_TINY_C7_ULTRA (default: ON)
const char* c7_env = getenv("HAKMEM_TINY_C7_ULTRA_ENABLED");
if (c7_env && *c7_env) {
snap->tiny_c7_ultra_enabled = (*c7_env != '0');
} else {
snap->tiny_c7_ultra_enabled = true; // default: ON
}
// Read HAKMEM_TINY_FRONT_V3_ENABLED (default: ON)
const char* v3_env = getenv("HAKMEM_TINY_FRONT_V3_ENABLED");
if (v3_env && *v3_env) {
snap->tiny_front_v3_enabled = (*v3_env != '0');
} else {
snap->tiny_front_v3_enabled = true; // default: ON
}
// Read HAKMEM_TINY_METADATA_CACHE (default: OFF)
const char* cache_env = getenv("HAKMEM_TINY_METADATA_CACHE");
if (cache_env && *cache_env) {
snap->tiny_metadata_cache = (*cache_env == '1');
} else {
snap->tiny_metadata_cache = false; // default: OFF
}
// Compute effective metadata cache (cache && !learner)
// Safety: disable if learner v7 is active (learner updates route_kind dynamically)
bool learner_active = small_learner_v2_enabled();
snap->tiny_metadata_cache_eff = snap->tiny_metadata_cache && !learner_active;
#if !HAKMEM_BUILD_RELEASE
fprintf(stderr, "[HAKMEM_ENV_SNAPSHOT] Initialized:\n");
fprintf(stderr, " tiny_c7_ultra_enabled: %d\n", snap->tiny_c7_ultra_enabled);
fprintf(stderr, " tiny_front_v3_enabled: %d\n", snap->tiny_front_v3_enabled);
fprintf(stderr, " tiny_metadata_cache: %d\n", snap->tiny_metadata_cache);
fprintf(stderr, " tiny_metadata_cache_eff: %d (learner_active=%d)\n",
snap->tiny_metadata_cache_eff, learner_active);
fflush(stderr);
#endif
}
// Initialize snapshot (lazy init on first access)
void hakmem_env_snapshot_init(void) {
if (g_hakmem_env_snapshot_ready) {
return; // already initialized
}
hakmem_env_snapshot_load(&g_hakmem_env_snapshot);
g_hakmem_env_snapshot_ready = 1;
}
// Refresh snapshot from ENV (for bench_profile putenv sync)
// This ensures that after bench_setenv_default() runs, the snapshot is refreshed
void hakmem_env_snapshot_refresh_from_env(void) {
// Refresh gate state too so bench_profile putenv defaults take effect even if
// the gate was lazily initialized earlier (e.g. by pre-main malloc/free).
const char* ctor_env = getenv("HAKMEM_ENV_SNAPSHOT_CTOR");
g_hakmem_env_snapshot_ctor_mode = (ctor_env && *ctor_env == '1') ? 1 : 0;
const char* gate_env = getenv("HAKMEM_ENV_SNAPSHOT");
g_hakmem_env_snapshot_gate = (gate_env && *gate_env == '1') ? 1 : 0;
hakmem_env_snapshot_load(&g_hakmem_env_snapshot);
g_hakmem_env_snapshot_ready = 1;
#if !HAKMEM_BUILD_RELEASE
fprintf(stderr, "[HAKMEM_ENV_SNAPSHOT] Refreshed from ENV (bench_profile sync)\n");
fflush(stderr);
#endif
}