# The directory that contains the hadoop configuration files.
# Don't change this unless you know what you're doing!
HADOOP_CONF_DIR=/etc/hadoop-0.20/conf

# The server that will act as the namenode.  This must match the
# output of 'hostname -s' on the namenode server so that
# /etc/init.d/hadoop can identify when it is being run on the namenode.
HADOOP_NAMENODE=SE-0-1

# The port that the namenode will listen on.  This is usually set to
# 9000 unless you are running an unsupported configuration with
# a datanode and namenode on the same host.
HADOOP_NAMEPORT=<MODIFIED FOR OUR PROTECTION - CHECK THE OSG HADOOP GUIDE FOR DETAILS>

# The host:port for accessing the namenode web interface.  This is
# used by the checkpoint server for getting checkpoints.
HADOOP_PRIMARY_HTTP_ADDRESS=${HADOOP_NAMENODE}:<MODIFIED FOR OUR PROTECTION - CHECK THE OSG HADOOP GUIDE FOR DETAILS>

# Default number of replicas requested by the client.  The default
# number of replicas for each file is a _client_ side setting, not
# a setting on the namenode.
HADOOP_REPLICATION_DEFAULT=2

# Minimum number of replicas allowed by the server.  1 is a good
# value.  Clients will not be able to request fewer than this
# number of replicas.
HADOOP_REPLICATION_MIN=1

# Maximum number of replicas allowed by the server.  Clients will
# not be able to requeset more than this number of replicas.
HADOOP_REPLICATION_MAX=512

# The user that the hadoop datanode and checkpoint server processes will run as.
HADOOP_USER=<MODIFIED FOR OUR PROTECTION - CHECK THE OSG HADOOP GUIDE FOR DETAILS>

# The base directory where most datanode files are stored
HADOOP_DATADIR=/scratch/hadoop

# The directory that will store the actual hdfs data on this datanode
# Multiple directories can be specified using a comma-separated list of
# directory names (with no spaces)
HADOOP_DATA=/hadoop1/data,/hadoop2/data

# The directory where the namenode/datanode log files are stored
HADOOP_LOG=${HADOOP_DATADIR}/log

# The directory where the namenode stores the hdfs namespace
HADOOP_SCRATCH=${HADOOP_DATADIR}/scratch

# Set this to an empty string to have the hadoop-firstboot script
# try to determine the ganglia multicast address from /etc/gmond.conf
HADOOP_GANGLIA_ADDRESS=hepcms-hn
HADOOP_GANGLIA_PORT=<MODIFIED FOR OUR PROTECTION - CHECK THE OSG HADOOP GUIDE FOR DETAILS>
# The interval, in seconds, at which metrics are reported to Ganglia.
HADOOP_GANGLIA_INTERVAL=10

# The name of the checkpoint server.  This must match the output
# of 'hostname -s' so that the hadoop init script knows where
# to start the checkpoint service.
HADOOP_SECONDARY_NAMENODE=interactive-0-0
HADOOP_SECONDARY_HTTP_ADDRESS=${HADOOP_SECONDARY_NAMENODE}:<MODIFIED FOR OUR PROTECTION - CHECK THE OSG HADOOP GUIDE FOR DETAILS>

# Comma-separated list of directories that will be used for storing namenode
# checkpoints.  At least one of these should be on nfs.
HADOOP_CHECKPOINT_DIRS=/scratch/hadoop/checkpoint1,/scratch/hadoop/checkpoint2,/share/apps/hadoop/checkpoint

# The interval, in seconds, between checkpoints.  Set to 3600 to
# generate a checkpoint once per hour.  If set to 3600, then if
# the namenode gets corrupted then you should not lose any
# namespace changes that are > 1 hour old.
HADOOP_CHECKPOINT_PERIOD=600

# The default block size for files in hdfs.  The default is 128M.
HADOOP_DATANODE_BLOCKSIZE=134217728

# The jvm heap size for the namenode.  The rule of thumb is a
# minimum of 1GB per million hdfs blocks.  With a 128MB block
# size, this comes out to roughly 1GB per 128TB of storage space.
HADOOP_NAMENODE_HEAP=2048

# The minimum size of the hadoop data directory, in GB.  The hadoop init
# script checks that the partition is at least this size before
# attempting to start the datanode.  This can be used to prevent starting
# a datanode on systems that don't have very much data space.  Set to
# zero to skip this check
HADOOP_MIN_DATANODE_SIZE=0

# The name of a script that takes a list of IP addresses and returns
# a list of rack names.  Hadoop uses this to make rack-aware intelligent
# decisions for data block replication.
HADOOP_RACKAWARE_SCRIPT=

# The central syslog collector.  If set, then logs will be sent to the
# syslog server in addition to being stored locally.
HADOOP_SYSLOG_HOST=

# Set this to '1' to automatically update fstab with an entry for 
# the hadoop fuse mount on /mnt/hadoop.  If you prefer to add this manually,
# then you will need to add the following to fstab, replacing 'namenode.host'
# with the fqdn of your namenode.
# hdfs# /mnt/hadoop fuse server=namenode.host,port=9000,rdbuffer=131072,allow_other 0 0
HADOOP_UPDATE_FSTAB=0