org.apache.cassandra.hadoop
Class ConfigHelper

java.lang.Object
  org.apache.cassandra.hadoop.ConfigHelper

public class ConfigHelper
extends java.lang.Object

Constructor Summary

ConfigHelper()

Method Summary

static org.apache.cassandra.thrift.Cassandra.Client	createConnection(java.lang.String host, java.lang.Integer port, boolean framed)
static org.apache.cassandra.thrift.Cassandra.Client	getClientFromAddressList(org.apache.hadoop.conf.Configuration conf)
static java.lang.String	getInitialAddress(org.apache.hadoop.conf.Configuration conf)
static java.lang.String	getInputColumnFamily(org.apache.hadoop.conf.Configuration conf)
static org.apache.cassandra.thrift.KeyRange	getInputKeyRange(org.apache.hadoop.conf.Configuration conf) may be null if unset
static java.lang.String	getInputKeyspace(org.apache.hadoop.conf.Configuration conf)
static java.lang.String	getInputKeyspacePassword(org.apache.hadoop.conf.Configuration conf)
static java.lang.String	getInputKeyspaceUserName(org.apache.hadoop.conf.Configuration conf)
static org.apache.cassandra.thrift.SlicePredicate	getInputSlicePredicate(org.apache.hadoop.conf.Configuration conf)
static int	getInputSplitSize(org.apache.hadoop.conf.Configuration conf)
static java.lang.String	getOutputColumnFamily(org.apache.hadoop.conf.Configuration conf)
static java.lang.String	getOutputKeyspace(org.apache.hadoop.conf.Configuration conf)
static java.lang.String	getOutputKeyspacePassword(org.apache.hadoop.conf.Configuration conf)
static java.lang.String	getOutputKeyspaceUserName(org.apache.hadoop.conf.Configuration conf)
static IPartitioner	getPartitioner(org.apache.hadoop.conf.Configuration conf)
static int	getRangeBatchSize(org.apache.hadoop.conf.Configuration conf) The number of rows to request with each get range slices request.
static java.lang.String	getRawInputSlicePredicate(org.apache.hadoop.conf.Configuration conf)
static java.lang.String	getReadConsistencyLevel(org.apache.hadoop.conf.Configuration conf)
static int	getRpcPort(org.apache.hadoop.conf.Configuration conf)
static java.lang.String	getWriteConsistencyLevel(org.apache.hadoop.conf.Configuration conf)
static void	setInitialAddress(org.apache.hadoop.conf.Configuration conf, java.lang.String address)
static void	setInputColumnFamily(org.apache.hadoop.conf.Configuration conf, java.lang.String keyspace, java.lang.String columnFamily) Set the keyspace and column family for the input of this job.
static void	setInputRange(org.apache.hadoop.conf.Configuration conf, java.lang.String startToken, java.lang.String endToken) Set the KeyRange to limit the rows.
static void	setInputSlicePredicate(org.apache.hadoop.conf.Configuration conf, org.apache.cassandra.thrift.SlicePredicate predicate) Set the predicate that determines what columns will be selected from each row.
static void	setInputSplitSize(org.apache.hadoop.conf.Configuration conf, int splitsize) Set the size of the input split.
static void	setOutputColumnFamily(org.apache.hadoop.conf.Configuration conf, java.lang.String keyspace, java.lang.String columnFamily) Set the keyspace and column family for the output of this job.
static void	setPartitioner(org.apache.hadoop.conf.Configuration conf, java.lang.String classname)
static void	setRangeBatchSize(org.apache.hadoop.conf.Configuration conf, int batchsize) The number of rows to request with each get range slices request.
static void	setRpcPort(org.apache.hadoop.conf.Configuration conf, java.lang.String port)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

ConfigHelper

public ConfigHelper()

Method Detail

setInputColumnFamily

public static void setInputColumnFamily(org.apache.hadoop.conf.Configuration conf,
                                        java.lang.String keyspace,
                                        java.lang.String columnFamily)

Set the keyspace and column family for the input of this job. Comparator and Partitioner types will be read from storage-conf.xml.

Parameters:

conf - Job configuration you are about to run

keyspace -

columnFamily -

setOutputColumnFamily

public static void setOutputColumnFamily(org.apache.hadoop.conf.Configuration conf,
                                         java.lang.String keyspace,
                                         java.lang.String columnFamily)

Set the keyspace and column family for the output of this job.

Parameters:

conf - Job configuration you are about to run

keyspace -

columnFamily -

setRangeBatchSize

public static void setRangeBatchSize(org.apache.hadoop.conf.Configuration conf,
                                     int batchsize)

The number of rows to request with each get range slices request. Too big and you can either get timeouts when it takes Cassandra too long to fetch all the data. Too small and the performance will be eaten up by the overhead of each request.

Parameters:

conf - Job configuration you are about to run

batchsize - Number of rows to request each time

getRangeBatchSize

public static int getRangeBatchSize(org.apache.hadoop.conf.Configuration conf)

The number of rows to request with each get range slices request. Too big and you can either get timeouts when it takes Cassandra too long to fetch all the data. Too small and the performance will be eaten up by the overhead of each request.

Parameters:

conf - Job configuration you are about to run

Returns:

Number of rows to request each time

setInputSplitSize

public static void setInputSplitSize(org.apache.hadoop.conf.Configuration conf,
                                     int splitsize)

Set the size of the input split. This affects the number of maps created, if the number is too small the overhead of each map will take up the bulk of the job time.

Parameters:

conf - Job configuration you are about to run

splitsize - Size of the input split

getInputSplitSize

public static int getInputSplitSize(org.apache.hadoop.conf.Configuration conf)

setInputSlicePredicate

public static void setInputSlicePredicate(org.apache.hadoop.conf.Configuration conf,
                                          org.apache.cassandra.thrift.SlicePredicate predicate)

Set the predicate that determines what columns will be selected from each row.

Parameters:

conf - Job configuration you are about to run

predicate -

getInputSlicePredicate

public static org.apache.cassandra.thrift.SlicePredicate getInputSlicePredicate(org.apache.hadoop.conf.Configuration conf)

getRawInputSlicePredicate

public static java.lang.String getRawInputSlicePredicate(org.apache.hadoop.conf.Configuration conf)

setInputRange

public static void setInputRange(org.apache.hadoop.conf.Configuration conf,
                                 java.lang.String startToken,
                                 java.lang.String endToken)

Set the KeyRange to limit the rows.

Parameters:

conf - Job configuration you are about to run

getInputKeyRange

public static org.apache.cassandra.thrift.KeyRange getInputKeyRange(org.apache.hadoop.conf.Configuration conf)

may be null if unset

getInputKeyspace

public static java.lang.String getInputKeyspace(org.apache.hadoop.conf.Configuration conf)

getOutputKeyspace

public static java.lang.String getOutputKeyspace(org.apache.hadoop.conf.Configuration conf)

getInputKeyspaceUserName

public static java.lang.String getInputKeyspaceUserName(org.apache.hadoop.conf.Configuration conf)

getInputKeyspacePassword

public static java.lang.String getInputKeyspacePassword(org.apache.hadoop.conf.Configuration conf)

getOutputKeyspaceUserName

public static java.lang.String getOutputKeyspaceUserName(org.apache.hadoop.conf.Configuration conf)

getOutputKeyspacePassword

public static java.lang.String getOutputKeyspacePassword(org.apache.hadoop.conf.Configuration conf)

getInputColumnFamily

public static java.lang.String getInputColumnFamily(org.apache.hadoop.conf.Configuration conf)

getOutputColumnFamily

public static java.lang.String getOutputColumnFamily(org.apache.hadoop.conf.Configuration conf)

getReadConsistencyLevel

public static java.lang.String getReadConsistencyLevel(org.apache.hadoop.conf.Configuration conf)

getWriteConsistencyLevel

public static java.lang.String getWriteConsistencyLevel(org.apache.hadoop.conf.Configuration conf)

getRpcPort

public static int getRpcPort(org.apache.hadoop.conf.Configuration conf)

setRpcPort

public static void setRpcPort(org.apache.hadoop.conf.Configuration conf,
                              java.lang.String port)

getInitialAddress

public static java.lang.String getInitialAddress(org.apache.hadoop.conf.Configuration conf)

setInitialAddress

public static void setInitialAddress(org.apache.hadoop.conf.Configuration conf,
                                     java.lang.String address)

setPartitioner

public static void setPartitioner(org.apache.hadoop.conf.Configuration conf,
                                  java.lang.String classname)

getPartitioner

public static IPartitioner getPartitioner(org.apache.hadoop.conf.Configuration conf)

getClientFromAddressList

public static org.apache.cassandra.thrift.Cassandra.Client getClientFromAddressList(org.apache.hadoop.conf.Configuration conf)
                                                                             throws java.io.IOException

Throws:

java.io.IOException

createConnection

public static org.apache.cassandra.thrift.Cassandra.Client createConnection(java.lang.String host,
                                                                            java.lang.Integer port,
                                                                            boolean framed)
                                                                     throws java.io.IOException

Throws:

java.io.IOException