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

# A/B sweep for Mid (2–32KiB): RING_CAP × PROBES × DRAIN_MAX × LOMAX (trigger fixed=2)
# - Rebuilds libhakmem.so per RING_CAP
# - Runs larson with the given params
# - Saves logs and summary/CSV under docs/benchmarks/<timestamp>_AB_RCAP_PROBE_DRAIN

RUNTIME=${RUNTIME:-2}
THREADS_CSV=${THREADS:-"1,4"}
RCAPS=${RCAPS:-"8,16"}
PROBES=${PROBES:-"2,3"}
DRAINS=${DRAINS:-"32,64"}
LOMAX=${LOMAX:-"256,512"}
TRIGGER=${TRIGGER:-2}

ROOT_DIR="$(cd "$(dirname "$0")/.." && pwd)"
OUTDIR="$ROOT_DIR/docs/benchmarks/$(date +%Y%m%d_%H%M%S)_AB_RCAP_PROBE_DRAIN"
mkdir -p "$OUTDIR"
LARSON="$ROOT_DIR/mimalloc-bench/bench/larson/larson"

if [[ ! -x "$LARSON" ]]; then
  echo "larson not found: $LARSON" >&2
  exit 1
fi

echo "A/B (Mid 2–32KiB) RUNTIME=${RUNTIME}s THREADS=${THREADS_CSV}" | tee "$OUTDIR/summary.txt"
echo "RING_CAP={${RCAPS}} PROBES={${PROBES}} DRAIN_MAX={${DRAINS}} LOMAX={${LOMAX}} TRIGGER=${TRIGGER}" | tee -a "$OUTDIR/summary.txt"
echo "label,ring_cap,probes,drain_max,lomax,trigger,threads,throughput_ops_per_sec" > "$OUTDIR/summary.csv"

IFS=',' read -r -a TARR <<< "$THREADS_CSV"
IFS=',' read -r -a RARR <<< "$RCAPS"
IFS=',' read -r -a PARR <<< "$PROBES"
IFS=',' read -r -a DARR <<< "$DRAINS"
IFS=',' read -r -a LARR <<< "$LOMAX"

build_release() {
  local cap="$1"
  echo "[BUILD] make shared RING_CAP=${cap}"
  ( cd "$ROOT_DIR" && make -j4 clean >/dev/null && make -j4 shared RING_CAP="$cap" >/dev/null )
}

extract_tput() {
  # Try to extract integer throughput from larson/hakmem outputs.
  # Prefer lines like: "Throughput =  5998924 operations per second"
  awk '
    /Throughput/ && /operations per second/ {
      for (i=1;i<=NF;i++) if ($i ~ /^[0-9]+$/) { print $i; exit }
    }
  ' || true
}

for rc in "${RARR[@]}"; do
  build_release "$rc"
  LIB="$(readlink -f "$ROOT_DIR/libhakmem.so")"
  for pr in "${PARR[@]}"; do
    for dm in "${DARR[@]}"; do
      for lm in "${LARR[@]}"; do
        for t in "${TARR[@]}"; do
          label="rc${rc}_pr${pr}_dm${dm}_lo${lm}_T${t}"
          echo "== $label ==" | tee -a "$OUTDIR/summary.txt"
          log="$OUTDIR/${label}.log"
          # Run with Mid band (2–32KiB), burst pattern (10000×1)
          if ! env HAKMEM_HDR_LIGHT=1 HAKMEM_POOL_TLS_RING=1 HAKMEM_SHARD_MIX=1 \
                 HAKMEM_TRYLOCK_PROBES="$pr" HAKMEM_RING_RETURN_DIV=3 \
                 HAKMEM_TC_ENABLE=1 HAKMEM_TC_DRAIN_MAX="$dm" HAKMEM_TC_DRAIN_TRIGGER="$TRIGGER" HAKMEM_TLS_LO_MAX="$lm" \
                 LD_PRELOAD="$LIB" "$LARSON" "$RUNTIME" 2048 32768 10000 1 12345 "$t" \
                 2>&1 | tee "$log" | tail -n 3 | tee -a "$OUTDIR/summary.txt" ; then
            echo "[WARN] run failed: $label" | tee -a "$OUTDIR/summary.txt"
          fi
          # Extract throughput
          tput="$(extract_tput < "$log")"
          [[ -z "$tput" ]] && tput=0
          echo "$label,$rc,$pr,$dm,$lm,$TRIGGER,$t,$tput" >> "$OUTDIR/summary.csv"
        done
      done
    done
  done
done

echo "Saved: $OUTDIR"

# Print top-5 by 4T if present, else 1T
if grep -q ',4,' "$OUTDIR/summary.csv"; then
  echo "\nTop-5 (4T):"
  sort -t, -k8,8nr "$OUTDIR/summary.csv" | awk -F, '$7==4' | head -n 5
fi

echo "\nTop-5 (1T):"
sort -t, -k8,8nr "$OUTDIR/summary.csv" | awk -F, '$7==1' | head -n 5

echo "\nBest 4T row (if present):"
best4=$(sort -t, -k8,8nr "$OUTDIR/summary.csv" | awk -F, '$7==4' | head -n 1 || true)
echo "$best4"