bigquery: add simple benchmarks

Benchmarks make various queries and measure
1. how long until we get the first row
2. how long we need to go through all rows

packages/bigquery/benchmark/README.md

@@ -0,0 +1,8 @@
+# BigQuery Benchmark
+This directory contains benchmarks for BigQuery client.
+
+## Usage
+`node bench.js queries.json`
+
+BigQuery service caches requests so the benchmark should be run
+at least twice, disregarding the first result.

packages/bigquery/benchmark/bench.js

@@ -0,0 +1,68 @@
+/*!
+ * Copyright 2014 Google Inc. All Rights Reserved.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+const util = require('util');
+const fs = require('fs');
+const BigQuery = require('../src/index.js');
+
+if (process.argv.length < 3) {
+ throw util.format("need query file; usage: '%s %s <queries.json>'", process.argv[0], process.argv[1]);
+}
+var queryJson = fs.readFileSync(process.argv[2]);
+var queries = JSON.parse(queryJson);
+var client = BigQuery();
+
+var doQuery = function(queryTxt) {
+ var startMilli = new Date().getTime();
+ var numRows = 0;
+ var numCols;
+ var timeFirstByteMilli;
+
+ var query = {
+ query: queryTxt,
+ useLegacySql: false
+ };
+
+ client.createQueryStream(query)
+ .on('error', function(err) {
+ throw err;
+ })
+ .on('data', function(row) {
+ if (numRows == 0) {
+ numCols = Object.keys(row).length;
+ timeFirstByteMilli = new Date().getTime() - startMilli;
+ } else if (numCols != Object.keys(row).length) {
+ throw util.format("query %j: wrong number of columns, want %d got %d",
+ queryTxt,
+ numCols,
+ Object.keys(row).length);
+ }
+ numRows++;
+ })
+ .on('end', function() {
+ timeTotalMilli = new Date().getTime() - startMilli;
+ console.log(util.format("query %j: got %d rows, %d cols, first byte %d sec, total %d sec",
+ queryTxt,
+ numRows,
+ numCols,
+ timeFirstByteMilli/1000,
+ timeTotalMilli/1000));
+ });
+}
+
+for (queryTxt of queries) {
+ doQuery(queryTxt);
+}

packages/bigquery/benchmark/queries.json

@@ -0,0 +1,10 @@
+[
+ "SELECT * FROM `nyc-tlc.yellow.trips` LIMIT 10000",
+ "SELECT * FROM `nyc-tlc.yellow.trips` LIMIT 100000",
+ "SELECT * FROM `nyc-tlc.yellow.trips` LIMIT 1000000",
+ "SELECT title FROM `bigquery-public-data.samples.wikipedia` ORDER BY title LIMIT 1000",
+ "SELECT title, id, timestamp, contributor_ip FROM `bigquery-public-data.samples.wikipedia` WHERE title like 'Blo%' ORDER BY id",
+ "SELECT * FROM `bigquery-public-data.baseball.games_post_wide` ORDER BY gameId",
+ "SELECT * FROM `bigquery-public-data.samples.github_nested` WHERE repository.has_downloads ORDER BY repository.created_at LIMIT 10000",
+ "SELECT repo_name, path FROM `bigquery-public-data.github_repos.files` WHERE path LIKE '%.java' ORDER BY id LIMIT 1000000"
+]

packages/bigquery/package.json

@@ -70,7 +70,8 @@
  "scripts": {
  "publish-module": "node ../../scripts/publish.js bigquery",
  "test": "mocha test/*.js",
- "system-test": "mocha system-test/*.js --no-timeouts --bail"
+ "system-test": "mocha system-test/*.js --no-timeouts --bail",
+ "benchmark": "time node benchmark/bench.js benchmark/queries.json"
  },
  "license": "Apache-2.0",
  "engines": {