Question

我在我的应用程序中使用Cassandra Node js驱动程序，并且获取100k记录它需要5.1秒，但使用java驱动程序在2.7秒内也是如此。下面是我在java和node js中的模式和代码。

Cassandra表架构

CREATE TABLE transactions_data (
app_name text,
api_name text,
app_id text,
start_time timestamp,
duration int,
end_time timestamp,
node_id text,
request_body text,
request_parameter_name1 text,
request_parameter_name2 text,
request_parameter_name3 text,
request_parameter_name4 text,
request_parameter_name5 text,
request_parameter_value1 text,
request_parameter_value2 text,
request_parameter_value3 text,
request_parameter_value4 text,
request_parameter_value5 text,
response_body text,
response_parameter_name1 text,
response_parameter_name2 text,
response_parameter_name3 text,
response_parameter_name4 text,
response_parameter_name5 text,
response_parameter_value1 text,
response_parameter_value2 text,
response_parameter_value3 text,
response_parameter_value4 text,
response_parameter_value5 text,
responsestatus text,
responsestatuscode text,
transaction_id text,
PRIMARY KEY ((app_name, api_name, app_id), start_time)
);

Java代码

public class CassandraQueryPerformance {

private Cluster cluster;
private Session session;

private String query;

public CassandraQueryPerformance(String host,String query) throws 
IOException {
    this.query=query;
    cluster = Cluster.builder().addContactPoints(host)
            .withSocketOptions(new 
SocketOptions().setConnectTimeoutMillis(2000000)).build();
    session = cluster.connect();
}

public void performanceTest() throws IOException {
    Statement statement = new SimpleStatement(query);
    statement.setFetchSize(100000);
    statement.setReadTimeoutMillis(650000).enableTracing();

     ResultSet rs = session.execute(statement);

    ArrayList<Row> list = new ArrayList<>();
    for (com.datastax.driver.core.Row row : rs) {
        list.add(row);
    }
    System.out.println("list count "+list.size());
}


public void close() {
    cluster.close();
    session.close();
}

public static void main(String[] args) throws IOException {

    long startTime = System.currentTimeMillis();
    CassandraQueryPerformance cqp = new 
CassandraQueryPerformance(args[0],args[1]);

    long onlyQueryTime = System.currentTimeMillis();

    cqp.performanceTest();
    System.out.println("total time without open close " + 
(System.currentTimeMillis() - onlyQueryTime));

    cqp.close();

    System.out.println("total time " + (System.currentTimeMillis() - 
startTime));
}

}

节点js代码

    'use strict';

    const Hapi = require('hapi');
    const cassandra = require('cassandra-driver');

    const options1 = {
     contactPoints: ['abcserver:9042'],
     keyspace: 'demo'
    }

    const server = new Hapi.Server();
    server.connection({
        host: 'localhost',
        port: 9999
    });

    // Add the route
    server.route({
        method: 'GET',
        path:'/get-transaction',
        handler: function (request, reply) {

          let allResults = [];
          //console.time('client_initialize');
          var client = new cassandra.Client(options1);
         // console.timeEnd('client_initialize');

    var cqlQuery="SELECT start_time, end_time, duration FROM " + 
             "transactions_data WHERE app_name = 'app_name-100'"+
             " AND api_name ='api_name-1'"+ 
            " AND app_id='app_id_19999999' AND "+
            " start_time >= '2017-03-20 13:40:29' AND "+
            " start_time <= '2017-04-25 13:40:29' ";

          client.connect(function(err, response) {

            console.time('queryTime');
            const options = { prepare : true , fetchSize : 100000};
            let formattedRow;
            client.eachRow(cqlQuery, {}, options, function (n, row) {
                 allResults.push(row);
            }, function (err, result) {

                if (result && result.nextPage) {
                    result.nextPage();
                }
                else{
                    console.timeEnd('queryTime');
                    console.log("Total no of records...",allResults.length);
                    reply('success');
                }
             reply('Hello '+request.query.limit);
            });
          });

        }
    });

    server.start((err) => {

        if (err) {
            throw err;
        }
        console.log('Server running at:', server.info.uri);
    });

以毫秒为单位捕获的结果

Number of records   Node      Java       Difference
10k                 846.232    494       352.232
20k                 1115.307   624       491.307
30k                 1603.353   897       706.353
40k                 2124.656   1051     1073.656
50k                 2626.624   1437     1189.624
60k                 2940.313   1912     1028.313
70k                 3478.797   1866     1612.797
80k                 4293.986   2108     2185.986
90k                 4677.516   2228     2449.516
100k                5175.231   2379     2796.231

Answer 1

从NodeJS开始是单线程的，而java驱动程序不应该是。这可以使CPU密集型任务（例如解压缩或解析Cassandra记录）在NodeJS上运行缓慢。

在驱动程序实现级别上存在许多差异，首先是在客户端打开连接和完成记录构建所花费的时间。默认情况下也可能存在许多差异，例如使用或不使用压缩进行数据传输。

我已经使用python运行测试并且去了，并设法通过许多工作流程获得x10性能。 NodeJS和Java是非常不同的语言，默认情况下Java应该提供更好的性能。

为什么Cassandra Node js驱动程序比java慢

1 个答案: