MultiforaDB/tests/e2e/compare-run.sh

#!/bin/bash
# Compare mongo-lite against a real MongoDB with the same workload, same driver.
#
#   bash tests/e2e/compare-run.sh [size] [doc-size]
#   (defaults: 1g, 16k)
#
# Starts mongod on :27018 and mongo-lite on :27019, runs compare.js against
# each (durable writes: mongo-lite fsyncs per doc, mongod ack'd with j:true),
# measures kill -9 reopen time for both, and prints a side-by-side table.
set -u
cd "$(dirname "$0")/../.."
SIZE="${1:-1g}"
DOC="${2:-16k}"
echo "comparing mongo-lite vs mongodb — dataset ${SIZE}, docs ~${DOC}"

CMPDIR=/tmp/mongo-cmp
mkdir -p "$CMPDIR/mongod"
ML_LOG="$CMPDIR/ml.log"
ML_OUT="$CMPDIR/ml-srv.out"
MD_OUT="$CMPDIR/md-srv.out"
ML_PORT=27019
MD_PORT=27018
rm -f "$ML_LOG"
rm -rf "$CMPDIR/mongod" && mkdir -p "$CMPDIR/mongod"

# ---- MongoDB -------------------------------------------------------------
echo; echo "### mongod (MongoDB $(mongod --version | grep -oE 'v[0-9.]+' | head -1))"
mongod --dbpath "$CMPDIR/mongod" --port $MD_PORT --bind_ip 127.0.0.1 \
       --quiet >"$MD_OUT" 2>&1 &
MD_PID=$!
sleep 2
node tests/e2e/compare.js --url "mongodb://127.0.0.1:$MD_PORT" --label mongodb --size "$SIZE" --doc-size "$DOC" \
  > "$CMPDIR/mongo-report.txt" 2>&1 || { echo "mongodb bench failed:"; tail -5 "$CMPDIR/mongo-report.txt"; }
MD_RSS=$(ps -o rss= -p $MD_PID | awk '{printf "%.0f", $1/1024}')
MD_DISK=$(du -sm "$CMPDIR/mongod" | awk '{print $1}')

echo; echo "### mongod kill -9 + reopen"
kill -9 $MD_PID; wait $MD_PID 2>/dev/null
MD_REOPEN=$(cd tests/e2e && node -e '
const { spawn } = require("child_process");
const { MongoClient } = require("mongodb");
const t0 = Date.now();
const p = spawn("mongod", ["--dbpath","/tmp/mongo-cmp/mongod","--port","27018","--bind_ip","127.0.0.1","--quiet"], {stdio:"ignore"});
const poll = async () => {
  const c = new MongoClient("mongodb://127.0.0.1:27018", {serverSelectionTimeoutMS: 800});
  try { await c.connect(); await c.db("admin").command({ping:1}); await c.close(); p.kill("SIGKILL"); console.log(((Date.now()-t0)/1000).toFixed(1)); }
  catch { try { await c.close(); } catch {}; setTimeout(poll, 200); }
};
setTimeout(poll, 300);
')
kill -9 $MD_PID 2>/dev/null

# ---- mongo-lite ----------------------------------------------------------
echo; echo "### mongo-lite (recommended config: --compact-threshold 1g)"
# Debug is ~10-200x slower (see the README's perf section) — the comparison
# must use the optimized build.
zig build -Doptimize=ReleaseFast 2>&1 | grep -c "^error" | grep -q "^0" || { echo "build failed"; exit 1; }
./zig-out/bin/mongo-lite --port $ML_PORT --db "$ML_LOG" --compact-threshold 1g >"$ML_OUT" 2>&1 &
ML_PID=$!
sleep 1
node tests/e2e/compare.js --url "mongodb://127.0.0.1:$ML_PORT" --label mongo-lite --size "$SIZE" --doc-size "$DOC" \
  > "$CMPDIR/ml-report.txt" 2>&1 || { echo "mongo-lite bench failed:"; tail -5 "$CMPDIR/ml-report.txt"; }
ML_RSS=$(ps -o rss= -p $ML_PID | awk '{printf "%.0f", $1/1024}')
ML_DISK=$(du -sm "$ML_LOG" | awk '{print $1}')

echo; echo "### mongo-lite kill -9 + reopen (replay)"
kill -9 $ML_PID; wait $ML_PID 2>/dev/null
ML_REOPEN=$(cd tests/e2e && node -e '
const { spawn } = require("child_process");
const { MongoClient } = require("mongodb");
const t0 = Date.now();
const p = spawn("/Users/shkmv/workspace/sandbox/mongo-lite/zig-out/bin/mongo-lite", ["--port","27019","--db","/tmp/mongo-cmp/ml.log","--compact-threshold","1g"], {stdio:"ignore"});
const poll = async () => {
  const c = new MongoClient("mongodb://127.0.0.1:27019", {serverSelectionTimeoutMS: 800});
  try { await c.connect(); await c.db("admin").command({ping:1}); await c.close(); p.kill("SIGKILL"); console.log(((Date.now()-t0)/1000).toFixed(1)); }
  catch { try { await c.close(); } catch {}; setTimeout(poll, 200); }
};
setTimeout(poll, 300);
')
kill -9 $ML_PID 2>/dev/null

# ---- side by side ----------------------------------------------------------
echo; echo "### side by side — ${SIZE} dataset, ~${DOC} docs"
cat > "$CMPDIR/meta.json" <<EOF
{"ml_rss_mb": "$ML_RSS", "md_rss_mb": "$MD_RSS", "ml_reopen": "${ML_REOPEN}s", "md_reopen": "${MD_REOPEN}s", "ml_disk_mb": "${ML_DISK}MB", "md_disk_mb": "${MD_DISK}MB"}
EOF
node -e '
const fs = require("fs");
const read = (p) => {
  const m = {};
  if (!fs.existsSync(p)) return m;
  for (const line of fs.readFileSync(p, "utf8").split("\n")) {
    const i = line.indexOf("\t");
    if (i > 0) m[line.slice(0, i)] = line.slice(i + 1).replace(/\t.*$/, "");
  }
  return m;
};
const a = read("/tmp/mongo-cmp/ml-report.txt");
const b = read("/tmp/mongo-cmp/mongo-report.txt");
const meta = JSON.parse(fs.readFileSync("/tmp/mongo-cmp/meta.json", "utf8"));
const keys = ["insertOne (sequential) ×200","bulk insert throughput","docs loaded","createIndex({k: 1})",
  "countDocuments({})","findOne({_id: <ObjectId>})","findOne({k: 500}) (indexed)","find({p: {$gte,$lt}}).count() (scan)",
  "find({}).sort({_id:-1}).limit(20)","find({}, {proj}).limit(1000)","aggregate $group by k",
  "updateOne({_id}) ×50","updateMany({k: 7}, {$inc})","deleteOne({_id}) + insertOne","node client RSS"];
const col = (v) => String(v).padEnd(22);
console.log(`${"benchmark".padEnd(42)}  ${col("mongo-lite")}  ${col("mongodb")}  ratio`);
for (const k of keys) {
  const av = a[k] || "—", bv = b[k] || "—";
  const ar = parseFloat(av), br = parseFloat(bv);
  const ratio = isFinite(ar) && isFinite(br) && ar > 0 && br > 0 ? (ar / br).toFixed(1) + "x" : "";
  console.log(`${k.padEnd(42)}  ${col(av)}  ${col(bv)}  ${ratio}`);
}
console.log(`${`server RSS`.padEnd(42)}  ${col(meta.ml_rss_mb + " MB")}  ${col(meta.md_rss_mb + " MB")}`);
console.log(`${`kill -9 reopen`.padEnd(42)}  ${col(meta.ml_reopen)}  ${col(meta.md_reopen)}`);
console.log(`${`db on disk`.padEnd(42)}  ${col(meta.ml_disk_mb)}  ${col(meta.md_disk_mb)}`);
'

pkill -9 -f "mongo-lite --port $ML_PORT" 2>/dev/null
echo; echo "done — reports: $CMPDIR/ml-report.txt, $CMPDIR/mongo-report.txt"