Apache hama cluster scalability

Question

I am programming Apache Hama using the Hama graph API. I have a scalability problem when running my program in a cluster. The problem is that I am increasing the number of machines in the cluster, which, I believe, reduces the execution time, but I have more time to complete.

I run my program with a graph consisting of 8500 vertices. When using a cluster of 2 machines, the task takes 479 seconds, when using 3 machines, the job takes 503 seconds, when using 10 machines, the job takes 530 seconds. Can someone tell me what I am missing?

Here are my configuration data in a file hama-site.xml:

<configuration>
  <property>
    <name>bsp.master.address</name>
    <value>master</value>
  </property>
  <property>
    <name>bsp.system.dir</name>
    <value>/tmp/hama-hadoop/bsp/system</value>
  </property>
  <property>
     <name>bsp.local.dir</name>
     <value>/tmp/hama-hadoop/bsp/local</value>
  </property>
  <property>
    <name>hama.tmp.dir</name>
    <value>/tmp/hama-hadoop</value>
  </property>
  <property>
    <name>fs.default.name</name>
    <value>hdfs://master:54310</value>
  </property>
  <property>
    <name>hama.zookeeper.quorum</name>
    <value>master,slave1,slave2,slave3</value>
  </property>
</configuration>

File contents groomservers:

master
slave1
slave2
slave3

In the main method of my work, I have the following code:

public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration config = new Configuration();
        FileSystem hdfs = FileSystem.get(config);
        HamaConfiguration conf = new HamaConfiguration();
        GraphJob job = new GraphJob(conf, run.class);
        job.setJobName("job");

        BSPJobClient jobClient = new BSPJobClient(conf);
        ClusterStatus cluster = jobClient.getClusterStatus(true);
        job.setNumBspTask(cluster.getGroomServers());
        ...
        job.setPartitioner(HashPartitioner.class);
        ....
        if (matcherJob.waitForCompletion(true)) {
            System.out.println("Job Finished");

        }