sujee

// MembaseTest3
package tutorial;

import java.net.InetSocketAddress;
import java.util.concurrent.TimeUnit;

import net.spy.memcached.MemcachedClient;

/**
 * simulates writing / reading from two different clients

sujee

// MembaseTest1

package tutorial;
import java.net.InetSocketAddress;
import net.spy.memcached.MemcachedClient;
/**
 * Write / Read from Membase
 * 
 * @author sujee
 *

sujee

// MembaseTest2
package tutorial;

import java.net.InetSocketAddress;
import net.spy.memcached.MemcachedClient;

/**
 * simulates writing / reading from two different clients
 */
public class MembaseTest2

sujee

...
...
long t2 = System.currentTimeMillis();
cache.shutdown(10, TimeUnit.SECONDS); // graceful shutdown
System.out.println("Time for " + MAX + " puts is " + (t2 - t1) + " ms");

// open another connection
cache = new MemcachedClient(new InetSocketAddress(server, port));
...
...

sujee

#!/bin/bash

## http://sujee.net/tech/articles/amazon-emr-beyond-basics/

CLASS_DIR=classes

mkdir -p $CLASS_DIR
rm -rf $CLASS_DIR/*

# compile

sujee

/**
 * http://sujee.net/tech/articles/amazon-emr-beyond-basics/
 * takes one argument for input path
 */
public class TestMR extends Configured implements Tool
{

    public static void main(String[] args) throws Exception
    {
        int res = ToolRunner.run(new Configuration(), new TestMR(), args);

sujee

#!/bin/bash
## http://sujee.net/tech/articles/amazon-emr-beyond-basics/

# config
# if changing machine type, also change mapred config file
MASTER_INSTANCE_TYPE="m1.large"
SLAVE_INSTANCE_TYPE="c1.xlarge"
INSTANCES=5
export JOBNAME="MyMR"
export TIMESTAMP=$(date +%Y%m%d-%H%M%S)

sujee

#!/bin/bash
## http://sujee.net/tech/articles/amazon-emr-beyond-basics/

echo "=== $JOBID started...."

LOGDIR="/var/logs/hadoop-logs/${JOBNAME}__${JOBID}__${TIMESTAMP}"
mkdir -p "${LOGDIR}"

## stuff below is to wait till the jobs is done

sujee

require 'rubygems'
require 'json'

a = JSON::parse(ARGF.read)
#p a 
p a["JobFlows"][0]["ExecutionStatusDetail"]["State"]

sujee

package amazonemr;

import java.net.URI;
import java.util.Enumeration;
import java.util.Properties;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;