#!/usr/bin/env bash
set -euo pipefail

# Defensive: ensure timeout exists; if not, best-effort shim
if ! command -v timeout >/dev/null 2>&1; then
  echo "[warn] 'timeout' not found; runs may hang on bench bugs" >&2
  TIMEOUT() { "$@"; }
else
  TIMEOUT() { timeout --kill-after=2s "$@"; }
fi

# Perf-annotated Larson runs for system/mimalloc/HAKMEM without LD_PRELOAD.
# Writes results under scripts/bench_results/larson_perf_*.txt

ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")"/.. && pwd)"
cd "$ROOT_DIR"

OUT_DIR="scripts/bench_results"
mkdir -p "$OUT_DIR"

dur=${DUR:-2}
min=${MIN:-8}
max=${MAX:-128}
chunks=${CHUNKS:-1024}
rounds=${ROUNDS:-1}
seed=${SEED:-12345}
threads_csv=${THREADS:-1,4}

# Ensure builds
[[ -x ./larson_system ]] || make -s larson_system >/dev/null
MI_SO="${MIMALLOC_SO:-mimalloc-bench/extern/mi/out/release/libmimalloc.so}"
have_mi=0
if [[ -f "$MI_SO" ]]; then
  have_mi=1
  [[ -x ./larson_mi ]] || make -s larson_mi >/dev/null || have_mi=0
fi
[[ -x ./larson_hakmem ]] || make -s larson_hakmem >/dev/null

IFS=',' read -ra ts <<<"$threads_csv"

run_one() {
  local name=$1; shift
  local bin=$1; shift
  local thr=$1; shift
  local tag="${name}_${thr}T_${dur}s_${min}-${max}"
  local base="$OUT_DIR/larson_${tag}"
  local outfile="${base}.txt"
  local outlog="${base}.stdout"
  local errlog="${base}.stderr"
  : >"$outfile"; : >"$outlog"; : >"$errlog"

  echo "== $name threads=$thr ==" | tee -a "$outfile"

  # Warm-up quick run (avoid one-time inits skew). Always bounded by timeout.
  if [[ "$name" != "hakmem" ]]; then
    TIMEOUT "$((dur+2))"s "$bin" 1 "$min" "$max" "$chunks" "$rounds" "$seed" "$thr" \
      >>"$outlog" 2>>"$errlog" || true
  fi

  # Throughput run with timeout; capture both stdout/stderr to logs
  echo "[cmd] $bin $dur $min $max $chunks $rounds $seed $thr" | tee -a "$outfile"
  TIMEOUT "$((dur+3))"s "$bin" "$dur" "$min" "$max" "$chunks" "$rounds" "$seed" "$thr" \
    >>"$outlog" 2>>"$errlog" || true
  # Extract a single Throughput line from the captured stdout
  local tput_line
  if command -v rg >/dev/null 2>&1; then
    tput_line=$(rg -n "Throughput" -m 1 "$outlog" || true)
  else
    tput_line=$(grep -n "Throughput" "$outlog" | head -n1 || true)
  fi
  [[ -n "$tput_line" ]] && echo "$tput_line" | tee -a "$outfile" || echo "(no Throughput line)" | tee -a "$outfile"

  # perf stat (optional; if perf not present, skip gracefully)
  if command -v perf >/dev/null 2>&1; then
    TIMEOUT "$((dur+3))"s perf stat -o "$outfile" -a -d -d --append -- \
      "$bin" "$dur" "$min" "$max" "$chunks" "$rounds" "$seed" "$thr" \
      >>"$outlog" 2>>"$errlog" || true
  else
    echo "[warn] perf not found; skipping perf stat" | tee -a "$outfile"
  fi

  echo "[logs] stdout=$outlog stderr=$errlog" | tee -a "$outfile"
}

for t in "${ts[@]}"; do
  run_one system ./larson_system "$t"
  if (( have_mi == 1 )); then
    run_one mimalloc ./larson_mi "$t"
  fi
  HAKMEM_QUIET=1 HAKMEM_DISABLE_BATCH=1 HAKMEM_TINY_META_ALLOC=1 HAKMEM_TINY_META_FREE=1 \
  HAKMEM_TINY_USE_SUPERSLAB=${HAKMEM_TINY_USE_SUPERSLAB:-1} \
  HAKMEM_TINY_MUST_ADOPT=${HAKMEM_TINY_MUST_ADOPT:-1} \
    run_one hakmem ./larson_hakmem "$t"
done

echo "Written perf outputs under $OUT_DIR"