Benchmark for inserting wide rows into a Cassandra DB using both CQL and Thrift APIs

AstClient.java

package cassandra;

import java.util.Iterator;

import com.netflix.astyanax.ColumnListMutation;
import com.netflix.astyanax.serializers.AsciiSerializer;
import com.netflix.astyanax.serializers.LongSerializer;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import com.netflix.astyanax.AstyanaxContext;
import com.netflix.astyanax.Keyspace;
import com.netflix.astyanax.MutationBatch;
import com.netflix.astyanax.connectionpool.NodeDiscoveryType;
import com.netflix.astyanax.connectionpool.OperationResult;
import com.netflix.astyanax.connectionpool.exceptions.ConnectionException;
import com.netflix.astyanax.connectionpool.impl.ConnectionPoolConfigurationImpl;
import com.netflix.astyanax.connectionpool.impl.CountingConnectionPoolMonitor;
import com.netflix.astyanax.impl.AstyanaxConfigurationImpl;
import com.netflix.astyanax.model.Column;
import com.netflix.astyanax.model.ColumnFamily;
import com.netflix.astyanax.model.ColumnList;
import com.netflix.astyanax.thrift.ThriftFamilyFactory;

public class AstClient {
    private static final Logger logger = LoggerFactory.getLogger(AstClient.class);

    private AstyanaxContext<Keyspace> context;
    private Keyspace keyspace;
    private ColumnFamily<Long, String> EMP_CF;
    private static final String EMP_CF_NAME = "employees2";

    public void init() {
        logger.debug("init()");

        context = new AstyanaxContext.Builder()
                .forCluster("Test Cluster")
                .forKeyspace("test1")
                .withAstyanaxConfiguration(new AstyanaxConfigurationImpl()
                        .setDiscoveryType(NodeDiscoveryType.RING_DESCRIBE)
                )
                .withConnectionPoolConfiguration(new ConnectionPoolConfigurationImpl("MyConnectionPool")
                        .setPort(9160)
                        .setMaxConnsPerHost(1)
                        .setSeeds("127.0.0.1:9160")
                )
                .withAstyanaxConfiguration(new AstyanaxConfigurationImpl()
                        .setCqlVersion("3.0.0")
                        .setTargetCassandraVersion("2.0.5"))
                .withConnectionPoolMonitor(new CountingConnectionPoolMonitor())
                .buildKeyspace(ThriftFamilyFactory.getInstance());

        context.start();
        keyspace = context.getClient();

        EMP_CF = ColumnFamily.newColumnFamily(
                EMP_CF_NAME,
                LongSerializer.get(),
                AsciiSerializer.get());
    }

    public void insert(long time) {
        MutationBatch m = keyspace.prepareMutationBatch();

        ColumnListMutation<String> x =
                m.withRow(EMP_CF, time);
        for(int i=0;i<10000;i++)
            x.putColumn(Integer.toString(i), Integer.toString(i));

        try {
            @SuppressWarnings("unused")
            Object result = m.execute();
        } catch (ConnectionException e) {
            logger.error("failed to write data to C*", e);
            throw new RuntimeException("failed to write data to C*", e);
        }
        logger.debug("insert ok");
    }

    public void createCF() {
    }

    public void read(long time) {
        OperationResult<ColumnList<String>> result;
        try {
            result = keyspace.prepareQuery(EMP_CF)
                    .getKey(time)
                    .execute();

            ColumnList<String> cols = result.getResult();
            // process data

            // a) iterate over columsn
            for (Iterator<Column<String>> i = cols.iterator(); i.hasNext(); ) {
                Column<String> c = i.next();
                String v = c.getStringValue();
                System.out.println(c.getName() + " " + v);
            }

        } catch (ConnectionException e) {
            logger.error("failed to read from C*", e);
            throw new RuntimeException("failed to read from C*", e);
        }
    }

    public static void main(String[] args) {
        AstClient c = new AstClient();
        c.init();
        long t00 = System.nanoTime();
        for(int i=0;i<1000;i++) {
            long t0 = System.nanoTime();
            c.insert(i);
            long dt = System.nanoTime() - t0;
            System.out.println((1.0e9/dt) + " " + i);
        }
        long dtt = System.nanoTime() - t00;

        c.read(0);
        System.out.println(dtt / 1e9);
    }

}

CassandraTestMinimized.scala

package cassandra

import com.datastax.driver.core._

object CassandraTestMinimized extends App {

  val keyspace = "test"
  val table = "wide"
  val tableName = s"$keyspace.$table"

  def createKeyspace = s"""
CREATE KEYSPACE IF NOT EXISTS ${keyspace}
WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor' : 1 }
"""

  def createWideTable = s"""
CREATE TABLE IF NOT EXISTS ${tableName} (
time varchar,
name varchar,
value varchar,
PRIMARY KEY (time,name))
WITH COMPACT STORAGE
"""

  def writeTimeNameValue(time: String) = s"""
INSERT INTO ${tableName} (time, name, value)
VALUES ('$time', ?, ?)
"""

  val cluster = Cluster.builder.addContactPoints("127.0.0.1").build
  val session = cluster.connect()

  session.execute(createKeyspace)
  session.execute(createWideTable)

  for(i<-0 until 1000) {
    val entries =
      for {
        i <- 0 until 10000
        name = i.toString
        value = name
      } yield name -> value
    val batchPreparedStatement = writeMap(i, entries)
    val t0 = System.nanoTime()
    session.execute(batchPreparedStatement)
    val dt = System.nanoTime() - t0
    println(i + " " + (dt/1.0e9))
  }

  def writeMap(time: Long, update: Seq[(String, String)]) : BatchStatement = {
    val template = session
      .prepare(writeTimeNameValue(time.toString))
      .setConsistencyLevel(ConsistencyLevel.ONE)
    val batch = new BatchStatement(BatchStatement.Type.UNLOGGED)
    for ((k, v) <- update)
      batch.add(template.bind(k, v))
    batch
  }
}