Disk full while running hadoop - hadoop

Question

I ran a recursive map/reduce program. Something went wrong and it nearly consumes all the disk space available in C drive. So i closed the resource manager, node manager, Name Node, data node consoles.
Now i have a C drive which is almost full and i don't know how to empty the disk space and make my C drive as it was before. What should i do now. Any help is appreciated.
Here is the code
public class apriori {
public static class CandidateGenMap extends Mapper<LongWritable, Text, Text, Text>
{
private Text word = new Text();
private Text count = new Text();
private int Support = 5;
public void CandidatesGenRecursion(Vector<String> in, Vector<String> out,
int length, int level, int start,
Context context) throws IOException {
int i,size;
for(i=start;i<length;i++) {
if(level==0){
out.add(in.get(i));
} else {
out.add(in.get(i));
int init=1;
StringBuffer current = new StringBuffer();
for(String s:out)
{
if(init==1){
current.append(s);
init=0;
} else {
current.append(" ");
current.append(s);
}
}
word.set(current.toString());
count.set(Integer.toString(1));
try {
context.write(word, count);
} catch (InterruptedException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
if(i < length-1) {
CandidatesGenRecursion(in, out, length,level+1,i+1, context);
}
size = out.size();
if(size>0){
out.remove(size-1);
}
}
}
#Override
public void map(LongWritable key,Text value,Context context) throws IOException
{
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
String[] token=new String[2];
int i=0;
while(tokenizer.hasMoreTokens()){
token[i]= tokenizer.nextToken();
++i;
}
StringTokenizer urlToken = new StringTokenizer(token[1],",");
Vector<String> lst = new Vector<String>();
int loop=0;
while (urlToken.hasMoreTokens()) {
String str = urlToken.nextToken();
lst.add(str);
loop++;
}
Vector<String> combinations = new Vector<String>();
if(!lst.isEmpty()) {
CandidatesGenRecursion(lst, combinations, loop,0,0, context);
}
}
}
public static class CandidateGenReduce extends Reducer<Text, IntWritable, Text, IntWritable>
{
public void reduce(Text key,Iterator<IntWritable> values,Context context) throws IOException
{
int sum = 0;
while (values.hasNext()) {
sum += values.next().get();
}
try {
context.write(key, new IntWritable(sum));
} catch (InterruptedException e) {
e.printStackTrace();
}
}
}
public static void main(String[] args) throws Exception
{
Date dt;
long start,end; // Start and end time
//Start Timer
dt = new Date();
start = dt.getTime();
Configuration conf1 = new Configuration();
System.out.println("Starting Job2");
Job job2 = new Job(conf1, "apriori candidate gen");
job2.setJarByClass(apriori.class);
job2.setMapperClass(CandidateGenMap.class);
job2.setCombinerClass(CandidateGenReduce.class); //
job2.setReducerClass(CandidateGenReduce.class);
job2.setMapOutputKeyClass(Text.class);
job2.setMapOutputValueClass(Text.class);
job2.setOutputKeyClass(Text.class);
job2.setOutputValueClass(IntWritable.class);
job2.setInputFormatClass(TextInputFormat.class);
job2.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job2, new Path(args[0]));
FileOutputFormat.setOutputPath(job2, new Path(args[1]));
job2.waitForCompletion(true);
//End Timer
dt = new Date();
end = dt.getTime();
}
}

Answer 1

Hadoop needs sufficient disk space for its i/0 operations at each phase (map, reduce etc).

Answer 2

Check in your HDFS your job output path and delete the contents.
List contents:
$ sudo -u hdfs hadoop fs -ls [YourJobOutputPath]
Disk used:
$ sudo -u hdfs hadoop fs -du -h [YourJobOutputPath]
Delete contents (be careful!, it's recursive):
$ sudo -u hdfs hadoop fs -rm -R [YourJobOutputPath]

Answer 3

Deleting the output directory might help in freeing your disk from the files created by the MapReduce job.