Root Cause (identified via perf profiling): - shared_pool_acquire_slab() consumed 85% CPU (lock contention) - 19,372 locks/sec (1 lock per ~10 allocations) - Only ~64 blocks carved per SuperSlab refill → frequent lock acquisitions Fix Applied: 1. Increased HAKMEM_TINY_REFILL_DEFAULT from 64 → 128 blocks 2. Added larson targets to Pool TLS auto-enable in build.sh 3. Increased refill max ceiling from 256 → 512 (allows future tuning) Expected Impact: - Lock frequency: 19K → ~1.6K locks/sec (12x reduction) - Target performance: 0.74M → ~3-5M ops/sec (4-7x improvement) Known Issues: - Multi-threaded Larson (>1 thread) has pre-existing crash bug (NOT caused by this change) - Verified: Original code also crashes with >1 thread - Single-threaded Larson works fine: ~480-792K ops/sec - Root cause: "Node pool exhausted for class 7" → requires separate investigation Files Modified: - core/hakmem_build_flags.h: HAKMEM_TINY_REFILL_DEFAULT 64→128 - build.sh: Enable Pool TLS for larson targets Related: - Task agent report: LARSON_CATASTROPHIC_SLOWDOWN_ROOT_CAUSE.md - Priority 1 fix from 4-step optimization plan 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
164 lines
5.4 KiB
Bash
Executable File
164 lines
5.4 KiB
Bash
Executable File
#!/usr/bin/env bash
|
||
# build.sh - Unified build wrapper (Phase 7 + Pool TLS) with discoverable help
|
||
#
|
||
# Quick use:
|
||
# ./build.sh bench_pool_tls_hakmem # Recommended target
|
||
# ./build.sh help # Show usage/hints/ENV
|
||
# ./build.sh verify bench_pool_tls_hakmem # Check freshness
|
||
#
|
||
# Notes:
|
||
# - Flags are pinned to avoid drift (see below). You can pass extra make flags via
|
||
# EXTRA_MAKEFLAGS, e.g. EXTRA_MAKEFLAGS="HAKMEM_DEBUG_VERBOSE=1" ./build.sh <target>
|
||
# - Arena ENV (Pool TLS): HAKMEM_POOL_TLS_ARENA_MB_INIT/MAX/GROWTH_LEVELS
|
||
# - See also: docs/BUILDING_QUICKSTART.md
|
||
|
||
set -euo pipefail
|
||
|
||
FLAVOR="release"
|
||
if [[ $# -gt 0 && ( "$1" == "release" || "$1" == "debug" ) ]]; then
|
||
FLAVOR="$1"; shift
|
||
fi
|
||
TARGET="${1:-bench_mid_large_mt_hakmem}"
|
||
|
||
usage() {
|
||
cat <<'USAGE'
|
||
=========================================
|
||
HAKMEM Build Script (help)
|
||
=========================================
|
||
Usage:
|
||
./build.sh <target>
|
||
./build.sh help # Show this help
|
||
./build.sh list # Show common targets
|
||
./build.sh verify <bin> # Verify binary freshness
|
||
|
||
Common targets (curated):
|
||
- bench_random_mixed_hakmem
|
||
- bench_pool_tls_hakmem
|
||
- bench_mid_large_mt_hakmem
|
||
- larson_hakmem
|
||
|
||
Pinned build flags (by default):
|
||
POOL_TLS_PHASE1=1 HEADER_CLASSIDX=1 AGGRESSIVE_INLINE=1 PREWARM_TLS=1 POOL_TLS_PREWARM=1 POOL_TLS_BIND_BOX=1
|
||
|
||
Extra flags (optional):
|
||
Use environment var EXTRA_MAKEFLAGS, e.g.:
|
||
EXTRA_MAKEFLAGS="HAKMEM_DEBUG_VERBOSE=1" ./build.sh bench_pool_tls_hakmem
|
||
EXTRA_MAKEFLAGS="HAKMEM_TINY_SAFE_FREE=1" ./build.sh bench_random_mixed_hakmem
|
||
|
||
Pool TLS Arena ENV (A/B friendly):
|
||
export HAKMEM_POOL_TLS_ARENA_MB_INIT=2 # default 1
|
||
export HAKMEM_POOL_TLS_ARENA_MB_MAX=16 # default 8
|
||
export HAKMEM_POOL_TLS_ARENA_GROWTH_LEVELS=4 # default 3
|
||
|
||
Verify & perf tips:
|
||
make print-flags
|
||
./verify_build.sh <bin>
|
||
perf stat -e cycles,instructions,branches,branch-misses,cache-misses -r 3 -- ./<bin> ...
|
||
strace -e trace=mmap,madvise,munmap -c ./<bin> ...
|
||
USAGE
|
||
}
|
||
|
||
list_targets() {
|
||
cat <<'LIST'
|
||
Common build targets:
|
||
bench_random_mixed_hakmem # Tiny 1T mixed
|
||
bench_pool_tls_hakmem # Pool TLS (8–52KB)
|
||
bench_mid_large_mt_hakmem # Mid-Large MT (8–32KB)
|
||
larson_hakmem # Larson mixed
|
||
bench_random_mixed_system # glibc baseline
|
||
bench_pool_tls_system # glibc baseline (PoolTLS workload)
|
||
bench_mid_large_mt_system # glibc baseline (Mid-Large workload)
|
||
LIST
|
||
}
|
||
|
||
if [[ "${TARGET}" == "help" || "${TARGET}" == "-h" || "${TARGET}" == "--help" ]]; then
|
||
usage
|
||
exit 0
|
||
fi
|
||
|
||
if [[ "${TARGET}" == "list" ]]; then
|
||
list_targets
|
||
exit 0
|
||
fi
|
||
|
||
if [[ "${TARGET}" == "verify" ]]; then
|
||
BIN="${2:-}"
|
||
if [[ -z "${BIN}" ]]; then
|
||
echo "Usage: ./build.sh verify <binary>" >&2
|
||
exit 2
|
||
fi
|
||
./verify_build.sh "${BIN}"
|
||
exit 0
|
||
fi
|
||
|
||
echo "========================================="
|
||
echo " HAKMEM Build Script"
|
||
echo " Flavor: ${FLAVOR}"
|
||
echo " Target: ${TARGET}"
|
||
echo " Flags: POOL_TLS_PHASE1=${POOL_TLS_PHASE1:-0} POOL_TLS_PREWARM=${POOL_TLS_PREWARM:-0} POOL_TLS_BIND_BOX=${POOL_TLS_BIND_BOX:-0} DISABLE_MINCORE=${DISABLE_MINCORE:-0} HEADER_CLASSIDX=1 AGGRESSIVE_INLINE=1 PREWARM_TLS=1 ${EXTRA_MAKEFLAGS:-}"
|
||
echo "========================================="
|
||
|
||
# Always clean to avoid stale objects when toggling flags
|
||
make clean >/dev/null 2>&1 || true
|
||
|
||
# Phase 7 + Pool TLS defaults (pinned) + user extras
|
||
# Default: Target-specific Pool TLS settings
|
||
# - Mid-Large targets (8-34KB workloads) → Pool TLS ON (critical for performance)
|
||
# - Tiny targets (≤1KB workloads) → Pool TLS OFF (avoid TLS overhead for short benchmarks)
|
||
case "${TARGET}" in
|
||
bench_mid_large_mt_hakmem|bench_pool_tls_hakmem|bench_mid_large_mt_system|bench_pool_tls_system|larson_hakmem|larson_mi|larson_system)
|
||
POOL_TLS_PHASE1_DEFAULT=${POOL_TLS_PHASE1:-1} # ON for Mid-Large and mixed workloads
|
||
;;
|
||
*)
|
||
POOL_TLS_PHASE1_DEFAULT=${POOL_TLS_PHASE1:-0} # OFF for Tiny-focused benchmarks
|
||
;;
|
||
esac
|
||
POOL_TLS_PREWARM_DEFAULT=${POOL_TLS_PREWARM:-0}
|
||
POOL_TLS_BIND_BOX_DEFAULT=${POOL_TLS_BIND_BOX:-0}
|
||
DISABLE_MINCORE_DEFAULT=${DISABLE_MINCORE:-0}
|
||
|
||
MAKE_ARGS=(
|
||
BUILD_FLAVOR=${FLAVOR} \
|
||
POOL_TLS_PHASE1=${POOL_TLS_PHASE1_DEFAULT} \
|
||
POOL_TLS_PREWARM=${POOL_TLS_PREWARM_DEFAULT} \
|
||
POOL_TLS_BIND_BOX=${POOL_TLS_BIND_BOX_DEFAULT} \
|
||
DISABLE_MINCORE=${DISABLE_MINCORE_DEFAULT} \
|
||
HEADER_CLASSIDX=1 \
|
||
AGGRESSIVE_INLINE=1 \
|
||
PREWARM_TLS=1 \
|
||
)
|
||
|
||
# Apply debug flavor extras (non-invasive): verbose + safe-free optional
|
||
if [[ "${FLAVOR}" == "debug" ]]; then
|
||
MAKE_ARGS+=(HAKMEM_DEBUG_VERBOSE=1)
|
||
MAKE_ARGS+=(BUILD_RELEASE_DEFAULT=0) # Disable release mode for debug builds
|
||
# Uncomment to enable extra safety by default for debug runs (may slow hot path)
|
||
# MAKE_ARGS+=(HAKMEM_TINY_SAFE_FREE=1)
|
||
else
|
||
MAKE_ARGS+=(BUILD_RELEASE_DEFAULT=1) # Enable release mode for release builds
|
||
fi
|
||
|
||
# Append user-provided extras and target
|
||
if [[ -n "${EXTRA_MAKEFLAGS:-}" ]]; then
|
||
# shellcheck disable=SC2206
|
||
MAKE_ARGS+=(${EXTRA_MAKEFLAGS})
|
||
fi
|
||
MAKE_ARGS+=("${TARGET}")
|
||
|
||
make "${MAKE_ARGS[@]}"
|
||
|
||
echo ""
|
||
echo "========================================="
|
||
echo " ✅ Build successful"
|
||
echo " Run: ./${TARGET}"
|
||
echo "-----------------------------------------"
|
||
# Place artifacts under out/<flavor>/
|
||
OUTDIR="out/${FLAVOR}"
|
||
mkdir -p "${OUTDIR}"
|
||
if [[ -x "./${TARGET}" ]]; then
|
||
cp -f "./${TARGET}" "${OUTDIR}/${TARGET}"
|
||
echo " Saved: ${OUTDIR}/${TARGET}"
|
||
fi
|
||
echo " Tip: ./build.sh help # flags, ENV, targets"
|
||
echo "========================================="
|