2025-12-01 16:37:59 +09:00
|
|
|
hakmem_shared_pool.o: core/hakmem_shared_pool.c \
|
|
|
|
|
core/hakmem_shared_pool_internal.h core/hakmem_shared_pool.h \
|
2025-11-14 01:02:00 +09:00
|
|
|
core/superslab/superslab_types.h core/hakmem_tiny_superslab_constants.h \
|
|
|
|
|
core/hakmem_tiny_superslab.h core/superslab/superslab_inline.h \
|
2025-11-26 12:33:49 +09:00
|
|
|
core/superslab/superslab_types.h core/superslab/../tiny_box_geometry.h \
|
|
|
|
|
core/superslab/../hakmem_tiny_superslab_constants.h \
|
2025-12-10 09:08:18 +09:00
|
|
|
core/superslab/../hakmem_tiny_config.h \
|
|
|
|
|
core/superslab/../hakmem_super_registry.h \
|
|
|
|
|
core/superslab/../hakmem_tiny_superslab.h \
|
|
|
|
|
core/superslab/../box/ss_addr_map_box.h \
|
|
|
|
|
core/superslab/../box/../hakmem_build_flags.h \
|
Phase 3 D2: Wrapper Env Cache - [DECISION: NO-GO]
Target: Reduce wrapper_env_cfg() overhead in malloc/free hot path
- Strategy: Cache wrapper env configuration pointer in TLS
- Approach: Fast pointer cache (TLS caches const wrapper_env_cfg_t*)
Implementation:
- core/box/wrapper_env_cache_env_box.h: ENV gate (HAKMEM_WRAP_ENV_CACHE)
- core/box/wrapper_env_cache_box.h: TLS cache layer (wrapper_env_cfg_fast)
- core/box/hak_wrappers.inc.h: Integration into malloc/free hot paths
- ENV gate: HAKMEM_WRAP_ENV_CACHE=0/1 (default OFF)
A/B Test Results (Mixed, 10-run, 20M iters):
- Baseline (D2=0): 46.52M ops/s (avg), 46.47M ops/s (median)
- Optimized (D2=1): 45.85M ops/s (avg), 45.98M ops/s (median)
- Improvement: avg -1.44%, median -1.05% (DECISION: NO-GO)
Analysis:
- Regression cause: TLS cache adds overhead (branch + TLS access)
- wrapper_env_cfg() is already minimal (pointer return after simple check)
- Adding TLS caching layer makes it worse, not better
- Branch prediction penalty outweighs any potential savings
Cumulative Phase 2-3:
- B3: +2.89%, B4: +1.47%, C3: +2.20%
- D1: +1.06% (opt-in), D2: -1.44% (NO-GO)
- Total: ~7.2% (excluding D2)
Decision: FREEZE as research box (default OFF, regression confirmed)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2025-12-13 22:03:27 +09:00
|
|
|
core/superslab/../box/super_reg_box.h \
|
|
|
|
|
core/superslab/../box/ss_pt_lookup_box.h \
|
|
|
|
|
core/superslab/../box/ss_pt_types_box.h \
|
|
|
|
|
core/superslab/../box/ss_pt_env_box.h \
|
|
|
|
|
core/superslab/../box/ss_pt_env_box.h core/tiny_debug_ring.h \
|
2025-11-14 01:02:00 +09:00
|
|
|
core/hakmem_build_flags.h core/tiny_remote.h \
|
2025-11-28 17:10:32 +09:00
|
|
|
core/hakmem_tiny_superslab_constants.h core/hakmem_debug_master.h \
|
|
|
|
|
core/hakmem_stats_master.h core/box/ss_slab_meta_box.h \
|
2025-11-26 12:33:49 +09:00
|
|
|
core/box/../superslab/superslab_types.h core/box/slab_freelist_atomic.h \
|
|
|
|
|
core/box/tiny_next_ptr_box.h core/hakmem_tiny_config.h \
|
|
|
|
|
core/tiny_nextptr.h core/tiny_region_id.h core/tiny_box_geometry.h \
|
2025-12-10 09:08:18 +09:00
|
|
|
core/ptr_track.h core/hakmem_tiny.h core/hakmem_trace.h \
|
|
|
|
|
core/hakmem_tiny_mini_mag.h core/box/hak_lane_classify.inc.h \
|
|
|
|
|
core/box/ptr_type_box.h core/tiny_debug_api.h core/box/tiny_layout_box.h \
|
Phase 3 D2: Wrapper Env Cache - [DECISION: NO-GO]
Target: Reduce wrapper_env_cfg() overhead in malloc/free hot path
- Strategy: Cache wrapper env configuration pointer in TLS
- Approach: Fast pointer cache (TLS caches const wrapper_env_cfg_t*)
Implementation:
- core/box/wrapper_env_cache_env_box.h: ENV gate (HAKMEM_WRAP_ENV_CACHE)
- core/box/wrapper_env_cache_box.h: TLS cache layer (wrapper_env_cfg_fast)
- core/box/hak_wrappers.inc.h: Integration into malloc/free hot paths
- ENV gate: HAKMEM_WRAP_ENV_CACHE=0/1 (default OFF)
A/B Test Results (Mixed, 10-run, 20M iters):
- Baseline (D2=0): 46.52M ops/s (avg), 46.47M ops/s (median)
- Optimized (D2=1): 45.85M ops/s (avg), 45.98M ops/s (median)
- Improvement: avg -1.44%, median -1.05% (DECISION: NO-GO)
Analysis:
- Regression cause: TLS cache adds overhead (branch + TLS access)
- wrapper_env_cfg() is already minimal (pointer return after simple check)
- Adding TLS caching layer makes it worse, not better
- Branch prediction penalty outweighs any potential savings
Cumulative Phase 2-3:
- B3: +2.89%, B4: +1.47%, C3: +2.20%
- D1: +1.06% (opt-in), D2: -1.44% (NO-GO)
- Total: ~7.2% (excluding D2)
Decision: FREEZE as research box (default OFF, regression confirmed)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2025-12-13 22:03:27 +09:00
|
|
|
core/box/../hakmem_tiny_config.h core/box/../hakmem_build_flags.h \
|
|
|
|
|
core/box/tiny_header_box.h core/box/tiny_layout_box.h \
|
2025-12-14 16:28:23 +09:00
|
|
|
core/box/../tiny_region_id.h core/box/tiny_header_write_once_env_box.h \
|
|
|
|
|
core/box/ss_hot_cold_box.h core/box/pagefault_telemetry_box.h \
|
|
|
|
|
core/box/tls_sll_drain_box.h core/box/tls_sll_box.h \
|
|
|
|
|
core/box/../hakmem_internal.h core/box/../hakmem.h \
|
|
|
|
|
core/box/../hakmem_build_flags.h core/box/../hakmem_config.h \
|
|
|
|
|
core/box/../hakmem_features.h core/box/../hakmem_sys.h \
|
|
|
|
|
core/box/../hakmem_whale.h core/box/../box/ptr_type_box.h \
|
|
|
|
|
core/box/../hakmem_debug_master.h core/box/../tiny_remote.h \
|
|
|
|
|
core/box/../hakmem_tiny_integrity.h core/box/../hakmem_tiny.h \
|
|
|
|
|
core/box/../ptr_track.h core/box/../ptr_trace.h \
|
|
|
|
|
core/box/../hakmem_trace_master.h core/box/../hakmem_stats_master.h \
|
|
|
|
|
core/box/../tiny_debug_ring.h core/box/ss_addr_map_box.h \
|
|
|
|
|
core/box/../superslab/superslab_inline.h core/box/tiny_ptr_bridge_box.h \
|
2025-12-04 12:55:53 +09:00
|
|
|
core/box/../hakmem_tiny_superslab_internal.h \
|
|
|
|
|
core/box/../hakmem_tiny_superslab.h core/box/../box/ss_hot_cold_box.h \
|
|
|
|
|
core/box/../box/ss_allocation_box.h core/hakmem_tiny_superslab.h \
|
|
|
|
|
core/box/../hakmem_debug_master.h core/box/../hakmem_tiny_config.h \
|
|
|
|
|
core/box/../hakmem_internal.h core/box/../tiny_region_id.h \
|
|
|
|
|
core/box/../hakmem_tiny_integrity.h \
|
|
|
|
|
core/box/../box/slab_freelist_atomic.h core/box/tiny_header_box.h \
|
2025-12-07 22:49:28 +09:00
|
|
|
core/box/tiny_heap_env_box.h core/box/c7_hotpath_env_box.h \
|
2025-12-04 12:55:53 +09:00
|
|
|
core/box/slab_recycling_box.h core/box/../hakmem_tiny_superslab.h \
|
|
|
|
|
core/box/ss_hot_cold_box.h core/box/ss_release_guard_box.h \
|
|
|
|
|
core/box/free_local_box.h core/box/ptr_type_box.h \
|
|
|
|
|
core/box/free_publish_box.h core/hakmem_tiny.h core/tiny_region_id.h \
|
2025-12-07 03:12:27 +09:00
|
|
|
core/box/tls_slab_reuse_guard_box.h core/hakmem_policy.h \
|
|
|
|
|
core/box/shared_pool_box.h
|
2025-12-01 16:37:59 +09:00
|
|
|
core/hakmem_shared_pool_internal.h:
|
2025-11-14 01:02:00 +09:00
|
|
|
core/hakmem_shared_pool.h:
|
|
|
|
|
core/superslab/superslab_types.h:
|
|
|
|
|
core/hakmem_tiny_superslab_constants.h:
|
|
|
|
|
core/hakmem_tiny_superslab.h:
|
|
|
|
|
core/superslab/superslab_inline.h:
|
|
|
|
|
core/superslab/superslab_types.h:
|
2025-11-26 12:33:49 +09:00
|
|
|
core/superslab/../tiny_box_geometry.h:
|
|
|
|
|
core/superslab/../hakmem_tiny_superslab_constants.h:
|
|
|
|
|
core/superslab/../hakmem_tiny_config.h:
|
2025-12-10 09:08:18 +09:00
|
|
|
core/superslab/../hakmem_super_registry.h:
|
|
|
|
|
core/superslab/../hakmem_tiny_superslab.h:
|
|
|
|
|
core/superslab/../box/ss_addr_map_box.h:
|
|
|
|
|
core/superslab/../box/../hakmem_build_flags.h:
|
|
|
|
|
core/superslab/../box/super_reg_box.h:
|
Phase 3 D2: Wrapper Env Cache - [DECISION: NO-GO]
Target: Reduce wrapper_env_cfg() overhead in malloc/free hot path
- Strategy: Cache wrapper env configuration pointer in TLS
- Approach: Fast pointer cache (TLS caches const wrapper_env_cfg_t*)
Implementation:
- core/box/wrapper_env_cache_env_box.h: ENV gate (HAKMEM_WRAP_ENV_CACHE)
- core/box/wrapper_env_cache_box.h: TLS cache layer (wrapper_env_cfg_fast)
- core/box/hak_wrappers.inc.h: Integration into malloc/free hot paths
- ENV gate: HAKMEM_WRAP_ENV_CACHE=0/1 (default OFF)
A/B Test Results (Mixed, 10-run, 20M iters):
- Baseline (D2=0): 46.52M ops/s (avg), 46.47M ops/s (median)
- Optimized (D2=1): 45.85M ops/s (avg), 45.98M ops/s (median)
- Improvement: avg -1.44%, median -1.05% (DECISION: NO-GO)
Analysis:
- Regression cause: TLS cache adds overhead (branch + TLS access)
- wrapper_env_cfg() is already minimal (pointer return after simple check)
- Adding TLS caching layer makes it worse, not better
- Branch prediction penalty outweighs any potential savings
Cumulative Phase 2-3:
- B3: +2.89%, B4: +1.47%, C3: +2.20%
- D1: +1.06% (opt-in), D2: -1.44% (NO-GO)
- Total: ~7.2% (excluding D2)
Decision: FREEZE as research box (default OFF, regression confirmed)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2025-12-13 22:03:27 +09:00
|
|
|
core/superslab/../box/ss_pt_lookup_box.h:
|
|
|
|
|
core/superslab/../box/ss_pt_types_box.h:
|
|
|
|
|
core/superslab/../box/ss_pt_env_box.h:
|
|
|
|
|
core/superslab/../box/ss_pt_env_box.h:
|
2025-11-14 01:02:00 +09:00
|
|
|
core/tiny_debug_ring.h:
|
|
|
|
|
core/hakmem_build_flags.h:
|
|
|
|
|
core/tiny_remote.h:
|
|
|
|
|
core/hakmem_tiny_superslab_constants.h:
|
2025-11-28 17:10:32 +09:00
|
|
|
core/hakmem_debug_master.h:
|
|
|
|
|
core/hakmem_stats_master.h:
|
2025-11-20 07:32:30 +09:00
|
|
|
core/box/ss_slab_meta_box.h:
|
|
|
|
|
core/box/../superslab/superslab_types.h:
|
2025-11-26 12:33:49 +09:00
|
|
|
core/box/slab_freelist_atomic.h:
|
|
|
|
|
core/box/tiny_next_ptr_box.h:
|
|
|
|
|
core/hakmem_tiny_config.h:
|
|
|
|
|
core/tiny_nextptr.h:
|
|
|
|
|
core/tiny_region_id.h:
|
|
|
|
|
core/tiny_box_geometry.h:
|
|
|
|
|
core/ptr_track.h:
|
2025-11-28 01:45:45 +09:00
|
|
|
core/hakmem_tiny.h:
|
|
|
|
|
core/hakmem_trace.h:
|
|
|
|
|
core/hakmem_tiny_mini_mag.h:
|
2025-12-03 10:34:39 +09:00
|
|
|
core/box/hak_lane_classify.inc.h:
|
2025-12-01 16:37:59 +09:00
|
|
|
core/box/ptr_type_box.h:
|
2025-11-29 06:47:13 +09:00
|
|
|
core/tiny_debug_api.h:
|
2025-12-03 13:28:44 +09:00
|
|
|
core/box/tiny_layout_box.h:
|
|
|
|
|
core/box/../hakmem_tiny_config.h:
|
2025-12-10 09:08:18 +09:00
|
|
|
core/box/../hakmem_build_flags.h:
|
Phase 3 D2: Wrapper Env Cache - [DECISION: NO-GO]
Target: Reduce wrapper_env_cfg() overhead in malloc/free hot path
- Strategy: Cache wrapper env configuration pointer in TLS
- Approach: Fast pointer cache (TLS caches const wrapper_env_cfg_t*)
Implementation:
- core/box/wrapper_env_cache_env_box.h: ENV gate (HAKMEM_WRAP_ENV_CACHE)
- core/box/wrapper_env_cache_box.h: TLS cache layer (wrapper_env_cfg_fast)
- core/box/hak_wrappers.inc.h: Integration into malloc/free hot paths
- ENV gate: HAKMEM_WRAP_ENV_CACHE=0/1 (default OFF)
A/B Test Results (Mixed, 10-run, 20M iters):
- Baseline (D2=0): 46.52M ops/s (avg), 46.47M ops/s (median)
- Optimized (D2=1): 45.85M ops/s (avg), 45.98M ops/s (median)
- Improvement: avg -1.44%, median -1.05% (DECISION: NO-GO)
Analysis:
- Regression cause: TLS cache adds overhead (branch + TLS access)
- wrapper_env_cfg() is already minimal (pointer return after simple check)
- Adding TLS caching layer makes it worse, not better
- Branch prediction penalty outweighs any potential savings
Cumulative Phase 2-3:
- B3: +2.89%, B4: +1.47%, C3: +2.20%
- D1: +1.06% (opt-in), D2: -1.44% (NO-GO)
- Total: ~7.2% (excluding D2)
Decision: FREEZE as research box (default OFF, regression confirmed)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2025-12-13 22:03:27 +09:00
|
|
|
core/box/tiny_header_box.h:
|
2025-12-03 13:28:44 +09:00
|
|
|
core/box/tiny_layout_box.h:
|
|
|
|
|
core/box/../tiny_region_id.h:
|
2025-12-14 16:28:23 +09:00
|
|
|
core/box/tiny_header_write_once_env_box.h:
|
2025-11-21 04:56:48 +09:00
|
|
|
core/box/ss_hot_cold_box.h:
|
Phase 23 Unified Cache + PageFaultTelemetry generalization: Mid/VM page-fault bottleneck identified
Summary:
- Phase 23 Unified Cache: +30% improvement (Random Mixed 256B: 18.18M → 23.68M ops/s)
- PageFaultTelemetry: Extended to generic buckets (C0-C7, MID, L25, SSM)
- Measurement-driven decision: Mid/VM page-faults (80-100K) >> Tiny (6K) → prioritize Mid/VM optimization
Phase 23 Changes:
1. Unified Cache implementation (core/front/tiny_unified_cache.{c,h})
- Direct SuperSlab carve (TLS SLL bypass)
- Self-contained pop-or-refill pattern
- ENV: HAKMEM_TINY_UNIFIED_CACHE=1, HAKMEM_TINY_UNIFIED_C{0-7}=128
2. Fast path pruning (tiny_alloc_fast.inc.h, tiny_free_fast_v2.inc.h)
- Unified ON → direct cache access (skip all intermediate layers)
- Alloc: unified_cache_pop_or_refill() → immediate fail to slow
- Free: unified_cache_push() → fallback to SLL only if full
PageFaultTelemetry Changes:
3. Generic bucket architecture (core/box/pagefault_telemetry_box.{c,h})
- PF_BUCKET_{C0-C7, MID, L25, SSM} for domain-specific measurement
- Integration: hak_pool_try_alloc(), l25_alloc_new_run(), shared_pool_allocate_superslab_unlocked()
4. Measurement results (Random Mixed 500K / 256B):
- Tiny C2-C7: 2-33 pages, high reuse (64-3.8 touches/page)
- SSM: 512 pages (initialization footprint)
- MID/L25: 0 (unused in this workload)
- Mid/Large VM benchmarks: 80-100K page-faults (13-16x higher than Tiny)
Ring Cache Enhancements:
5. Hot Ring Cache (core/front/tiny_ring_cache.{c,h})
- ENV: HAKMEM_TINY_HOT_RING_ENABLE=1, HAKMEM_TINY_HOT_RING_C{0-7}=size
- Conditional compilation cleanup
Documentation:
6. Analysis reports
- RANDOM_MIXED_BOTTLENECK_ANALYSIS.md: Page-fault breakdown
- RANDOM_MIXED_SUMMARY.md: Phase 23 summary
- RING_CACHE_ACTIVATION_GUIDE.md: Ring cache usage
- CURRENT_TASK.md: Updated with Phase 23 results and Phase 24 plan
Next Steps (Phase 24):
- Target: Mid/VM PageArena/HotSpanBox (page-fault reduction 80-100K → 30-40K)
- Tiny SSM optimization deferred (low ROI, ~6K page-faults already optimal)
- Expected improvement: +30-50% for Mid/Large workloads
Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-17 02:47:58 +09:00
|
|
|
core/box/pagefault_telemetry_box.h:
|
2025-11-20 07:32:30 +09:00
|
|
|
core/box/tls_sll_drain_box.h:
|
|
|
|
|
core/box/tls_sll_box.h:
|
2025-12-01 16:37:59 +09:00
|
|
|
core/box/../hakmem_internal.h:
|
|
|
|
|
core/box/../hakmem.h:
|
|
|
|
|
core/box/../hakmem_build_flags.h:
|
|
|
|
|
core/box/../hakmem_config.h:
|
|
|
|
|
core/box/../hakmem_features.h:
|
|
|
|
|
core/box/../hakmem_sys.h:
|
|
|
|
|
core/box/../hakmem_whale.h:
|
|
|
|
|
core/box/../box/ptr_type_box.h:
|
2025-11-29 06:57:03 +09:00
|
|
|
core/box/../hakmem_debug_master.h:
|
2025-11-20 07:32:30 +09:00
|
|
|
core/box/../tiny_remote.h:
|
|
|
|
|
core/box/../hakmem_tiny_integrity.h:
|
|
|
|
|
core/box/../hakmem_tiny.h:
|
|
|
|
|
core/box/../ptr_track.h:
|
|
|
|
|
core/box/../ptr_trace.h:
|
2025-12-04 16:21:54 +09:00
|
|
|
core/box/../hakmem_trace_master.h:
|
|
|
|
|
core/box/../hakmem_stats_master.h:
|
2025-11-20 07:32:30 +09:00
|
|
|
core/box/../tiny_debug_ring.h:
|
2025-12-04 12:55:53 +09:00
|
|
|
core/box/ss_addr_map_box.h:
|
2025-11-21 23:00:24 +09:00
|
|
|
core/box/../superslab/superslab_inline.h:
|
2025-12-04 12:55:53 +09:00
|
|
|
core/box/tiny_ptr_bridge_box.h:
|
|
|
|
|
core/box/../hakmem_tiny_superslab_internal.h:
|
|
|
|
|
core/box/../hakmem_tiny_superslab.h:
|
|
|
|
|
core/box/../box/ss_hot_cold_box.h:
|
|
|
|
|
core/box/../box/ss_allocation_box.h:
|
|
|
|
|
core/hakmem_tiny_superslab.h:
|
|
|
|
|
core/box/../hakmem_debug_master.h:
|
|
|
|
|
core/box/../hakmem_tiny_config.h:
|
|
|
|
|
core/box/../hakmem_internal.h:
|
|
|
|
|
core/box/../tiny_region_id.h:
|
|
|
|
|
core/box/../hakmem_tiny_integrity.h:
|
|
|
|
|
core/box/../box/slab_freelist_atomic.h:
|
2025-11-30 15:27:53 +09:00
|
|
|
core/box/tiny_header_box.h:
|
2025-12-07 22:49:28 +09:00
|
|
|
core/box/tiny_heap_env_box.h:
|
|
|
|
|
core/box/c7_hotpath_env_box.h:
|
2025-11-30 15:27:53 +09:00
|
|
|
core/box/slab_recycling_box.h:
|
|
|
|
|
core/box/../hakmem_tiny_superslab.h:
|
|
|
|
|
core/box/ss_hot_cold_box.h:
|
2025-12-04 12:55:53 +09:00
|
|
|
core/box/ss_release_guard_box.h:
|
2025-11-20 07:32:30 +09:00
|
|
|
core/box/free_local_box.h:
|
2025-12-01 16:37:59 +09:00
|
|
|
core/box/ptr_type_box.h:
|
|
|
|
|
core/box/free_publish_box.h:
|
|
|
|
|
core/hakmem_tiny.h:
|
|
|
|
|
core/tiny_region_id.h:
|
2025-11-28 17:10:32 +09:00
|
|
|
core/box/tls_slab_reuse_guard_box.h:
|
2025-11-20 07:32:30 +09:00
|
|
|
core/hakmem_policy.h:
|
2025-12-07 03:12:27 +09:00
|
|
|
core/box/shared_pool_box.h:
|