cassandra 0.2.3 → 0.4

data/conf/cassandra.in.sh

@@ -0,0 +1,55 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+cassandra_home=`pwd`/cassandra
+
+# The directory where Cassandra's configs live (required)
+CASSANDRA_CONF=`pwd`/conf
+
+# This can be the path to a jar file, or a directory containing the 
+# compiled classes. NOTE: This isn't needed by the startup script,
+# it's just used here in constructing the classpath.
+cassandra_bin=$cassandra_home/build/classes
+#cassandra_bin=$cassandra_home/build/cassandra.jar
+
+# The java classpath (required)
+CLASSPATH=$CASSANDRA_CONF:$cassandra_bin
+
+for jar in $cassandra_home/lib/*.jar; do
+    CLASSPATH=$CLASSPATH:$jar
+done
+
+echo $cassandra_home
+
+# Arguments to pass to the JVM
+JVM_OPTS=" \
+        -ea \
+        -Xdebug \
+        -Xrunjdwp:transport=dt_socket,server=y,address=8888,suspend=n \
+        -Xms128M \
+        -Xmx1G \
+        -XX:SurvivorRatio=8 \
+        -XX:TargetSurvivorRatio=90 \
+        -XX:+AggressiveOpts \
+        -XX:+UseParNewGC \
+        -XX:+UseConcMarkSweepGC \
+        -XX:CMSInitiatingOccupancyFraction=1 \
+        -XX:+CMSParallelRemarkEnabled \
+        -XX:+HeapDumpOnOutOfMemoryError \
+        -Dcom.sun.management.jmxremote.port=8080 \
+        -Dcom.sun.management.jmxremote.ssl=false \
+        -Dcom.sun.management.jmxremote.authenticate=false"

data/conf/log4j.properties

@@ -0,0 +1,38 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# for production, you should probably set the root to INFO
+# and the pattern to %c instead of %l.  (%l is slower.)
+
+# output messages into a rolling log file as well as stdout
+log4j.rootLogger=DEBUG,stdout,R
+
+# stdout
+log4j.appender.stdout=org.apache.log4j.ConsoleAppender
+log4j.appender.stdout.layout=org.apache.log4j.SimpleLayout
+
+# rolling log file ("system.log
+log4j.appender.R=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.R.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.R.layout=org.apache.log4j.PatternLayout
+log4j.appender.R.layout.ConversionPattern=%5p [%t] %d{ISO8601} %F (line %L) %m%n
+# Edit the next line to point to your logs directory
+log4j.appender.R.File=data/logs/system.log
+
+# Application logging options
+#log4j.logger.com.facebook=DEBUG
+#log4j.logger.com.facebook.infrastructure.gms=DEBUG
+#log4j.logger.com.facebook.infrastructure.db=DEBUG

data/conf/storage-conf.xml

@@ -0,0 +1,197 @@
+<!--
+ ~ Licensed to the Apache Software Foundation (ASF) under one
+ ~ or more contributor license agreements.  See the NOTICE file
+ ~ distributed with this work for additional information
+ ~ regarding copyright ownership.  The ASF licenses this file
+ ~ to you under the Apache License, Version 2.0 (the
+ ~ "License"); you may not use this file except in compliance
+ ~ with the License.  You may obtain a copy of the License at
+ ~
+ ~    http:/www.apache.org/licenses/LICENSE-2.0
+ ~
+ ~ Unless required by applicable law or agreed to in writing,
+ ~ software distributed under the License is distributed on an
+ ~ "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ ~ KIND, either express or implied.  See the License for the
+ ~ specific language governing permissions and limitations
+ ~ under the License.
+ -->
+<Storage>
+    <!--======================================================================-->
+    <!-- Basic Configuration                                                  -->
+    <!--======================================================================-->
+    <ClusterName>Test</ClusterName>
+
+    <!-- Tables and ColumnFamilies                                            
+         Think of a table as a namespace, not a relational table.
+         (ColumnFamilies are closer in meaning to those.)
+
+         There is an implicit table named 'system' for Cassandra internals.
+    -->
+    <Tables>
+      <Table Name="Twitter">
+          <KeysCachedFraction>0.01</KeysCachedFraction>
+          <ColumnFamily CompareWith="UTF8Type" Name="Users" />
+          <ColumnFamily CompareWith="UTF8Type" Name="UserAudits" />
+          <ColumnFamily CompareWith="UTF8Type" CompareSubcolumnsWith="UUIDType" ColumnType="Super" Name="UserRelationships" />
+          <ColumnFamily CompareWith="UTF8Type" Name="Usernames" />
+          <ColumnFamily CompareWith="UTF8Type" Name="Statuses" />
+          <ColumnFamily CompareWith="UTF8Type" Name="StatusAudits" />
+          <ColumnFamily CompareWith="UTF8Type" CompareSubcolumnsWith="LongType" ColumnType="Super" Name="StatusRelationships" />  
+      </Table>
+
+      <Table Name="Multiblog">      
+        <KeysCachedFraction>0.01</KeysCachedFraction>
+        <ColumnFamily CompareWith="UTF8Type" Name="Blogs"/>
+        <ColumnFamily CompareWith="UTF8Type" Name="Comments"/>
+      </Table>
+    </Tables>
+
+    <!-- Partitioner: any IPartitioner may be used, including your own
+         as long as it is on the classpath.  Out of the box,
+         Cassandra provides
+         org.apache.cassandra.dht.RandomPartitioner and
+         org.apache.cassandra.dht.OrderPreservingPartitioner.
+         Range queries require using OrderPreservingPartitioner or a subclass.
+
+         Achtung!  Changing this parameter requires wiping your data directories,
+         since the partitioner can modify the sstable on-disk format.
+    -->
+    <Partitioner>org.apache.cassandra.dht.OrderPreservingPartitioner</Partitioner>
+
+    <!-- If you are using the OrderPreservingPartitioner and you know your key
+         distribution, you can specify the token for this node to use.
+         (Keys are sent to the node with the "closest" token, so distributing
+         your tokens equally along the key distribution space will spread
+         keys evenly across your cluster.)  This setting is only checked the
+         first time a node is started. 
+
+         This can also be useful with RandomPartitioner to force equal
+         spacing of tokens around the hash space, especially for
+         clusters with a small number of nodes. -->
+    <InitialToken></InitialToken>
+
+    <!-- RackAware: Setting this to true instructs Cassandra to try and place the replicas in
+         a different rack in the same datacenter and one in a different datacenter
+    -->
+    <RackAware>false</RackAware>
+
+    <!-- Number of replicas of the data-->
+    <ReplicationFactor>1</ReplicationFactor>
+
+    <!-- Directories: Specify where Cassandra should store different data on disk
+         Keep the data disks and the CommitLog disks separate for best performance
+    -->
+    <CommitLogDirectory>data/commitlog</CommitLogDirectory>
+    <DataFileDirectories>
+        <DataFileDirectory>data/data</DataFileDirectory>
+    </DataFileDirectories>
+    <CalloutLocation>data/callouts</CalloutLocation>
+    <BootstrapFileDirectory>data/bootstrap</BootstrapFileDirectory>
+    <StagingFileDirectory>data/staging</StagingFileDirectory>
+
+
+    <!-- Add names of hosts that are deemed contact points. Cassandra nodes use
+         this list of hosts to find each other and learn the topology of the ring.
+    -->
+    <Seeds>
+        <Seed>127.0.0.1</Seed>
+    </Seeds>
+
+    <!-- Miscellaneous -->
+
+    <!-- time to wait for a reply from other nodes before failing the command -->
+    <RpcTimeoutInMillis>5000</RpcTimeoutInMillis>
+    <!-- size to allow commitlog to grow to before creating a new segment -->
+    <CommitLogRotationThresholdInMB>128</CommitLogRotationThresholdInMB>
+
+
+    <!-- Local hosts and ports -->
+
+    <!-- Address to bind to and tell other nodes to connect to.  
+         You _must_ change this if you want multiple nodes to be able
+         to communicate!  
+
+         Leaving it blank leaves it up to InetAddress.getLocalHost(). 
+         This will always do the Right Thing *if* the node is properly
+         configured (hostname, name resolution, etc), and the Right
+         Thing is to use the address associated with the hostname (it
+         might not be). -->
+    <ListenAddress>localhost</ListenAddress>
+    <!-- TCP port, for commands and data -->
+    <StoragePort>7000</StoragePort>
+    <!-- UDP port, for membership communications (gossip) -->
+    <ControlPort>7001</ControlPort>
+
+    <!-- The address to bind the Thrift RPC service to. Unlike 
+         ListenAddress above, you *can* specify 0.0.0.0 here if you want
+         Thrift to listen on all interfaces.
+         
+         Leaving this blank has the same effect it does for ListenAddress,
+         (i.e. it will be based on the configured hostname of the node).
+    -->
+    <ThriftAddress>localhost</ThriftAddress>
+    <!-- Thrift RPC port (the port clients connect to). -->
+    <ThriftPort>9160</ThriftPort>
+
+
+    <!--======================================================================-->
+    <!-- Memory, Disk, and Performance                                        -->
+    <!--======================================================================-->
+
+    <!-- Add column indexes to a row after its contents reach this size -->
+    <ColumnIndexSizeInKB>256</ColumnIndexSizeInKB>
+
+    <!--
+      The maximum amount of data to store in memory before flushing to
+      disk. Note: There is one memtable per column family, and this threshold
+      is based solely on the amount of data stored, not actual heap memory
+      usage (there is some overhead in indexing the columns).
+    -->
+    <MemtableSizeInMB>32</MemtableSizeInMB>
+
+    <!--
+      The maximum number of columns in millions to store in memory
+      before flushing to disk.  This is also a per-memtable setting.
+      Use with MemtableSizeInMB to tune memory usage.
+    -->
+    <MemtableObjectCountInMillions>0.01</MemtableObjectCountInMillions>
+
+    <!-- Unlike most systems, in Cassandra writes are faster than
+         reads, so you can afford more of those in parallel.
+	 A good rule of thumb is 2 concurrent reads per processor core.
+         You especially want more concurrentwrites if you are using
+         CommitLogSync + CommitLogSyncDelay. -->
+    <ConcurrentReads>8</ConcurrentReads>
+    <ConcurrentWrites>32</ConcurrentWrites>
+
+    <!-- Turn on CommitLogSync to improve durability.
+         When enabled, Cassandra won't ack writes until the commit log
+         has been synced to disk.  This is less necessary in Cassandra
+         than in traditional databases since replication reduces the
+         odds of losing data from a failure after writing the log
+         entry but before it actually reaches the disk.
+    -->
+    <CommitLogSync>false</CommitLogSync>
+    <!-- Delay (in microseconds) during which additional commit log
+         entries may be written before fsync.  This will increase
+         latency slightly, but can vastly improve throughput where
+         there are many writers.  Set to zero to disable
+         (each entry will be synced individually).
+	 Reasonable values range from a minimal 100 to even 10000
+         if throughput matters more than latency.  (10000us = 10ms
+         write latency isn't even that bad by traditional db
+         standards.)
+    -->
+    <CommitLogSyncDelay>1000</CommitLogSyncDelay>
+         
+
+    <!-- Time to wait before garbage-collection deletion markers.
+         Set this to a large enough value that you are confident
+         that the deletion marker will be propagated to all replicas
+         by the time this many seconds has elapsed, even in the
+         face of hardware failures.  The default value is ten days.
+    -->
+    <GCGraceSeconds>864000</GCGraceSeconds>
+
+</Storage>

data/lib/cassandra.rb

@@ -1,160 +1,22 @@
-require 'properties'
-require 'tags'
 
-# Markaby-ish way to declare CSS
-class Cassandra
-  
-  METHODS = %w( class instance_eval send __send__ __id__ )
-  instance_methods.each { |m| undef_method( m ) unless METHODS.include? m }
-  
-  attr_reader :data
-  
-  def initialize(sel=nil)
-    @data = []
-    @selectors = [ sel ]
-    @properties = []
-    
-    # Primitive state machine
-    # possible states are :closed_block, :chain, :open_block
-    @state = :closed_block
-  end
-  
-  def self.process(*args,&block)
-    self.new.process(*args,&block)
-  end
-  
-  def process(*args, &block)
-    if block
-      instance_eval(&block)
-    else
-      instance_eval(args.join("\n"))
-    end
-    self
-  end
-  
-  def to_s
-    @data.map do |sel|
-      properties = sel.last.join("\n  ")
-      "#{sel.first} {\n  #{properties}\n}\n"
-    end.join
-  end
-
-
-
-  # Pushes an empty array on the properties stack and registers
-  # that array (against the current selector) in @data
-  def new_property_set
-    @properties.push []
-    @data << [@selectors[-1], @properties[-1] ]
-  end
-
-
-  # Declare a CSS selector using a block.  May be chained and nested.
-  def selector(sel)
-    if block_given?
-      open_block(sel)
-      yield
-      closed_block
-    else
-      chain(sel)
-    end
-    self
-  end
-  
-  # Catch unknown methods and treat them as CSS class or id selectors.
-  def method_missing(name, &block)
-    sel = selectify(name)
-    if block_given?
-      open_block(sel)
-      yield
-      closed_block
-    else
-      chain(sel)
-    end
-    self
-  end
-  
-  # bang methods represent CSS ids.  Otherwise CSS classes.
-  def selectify(method_name)
-    matches = method_name.to_s.match( /([\w_]+)!$/)
-    matches ? "##{matches[1]}" : ".#{method_name}"
-  end
-
-
-  # define tag methods that delegate to selector
-  methods =  HTML_TAGS.map do |tag|
-    <<-METHOD
-    def #{tag}(&block)
-      selector('#{tag}', &block)
-    end
-    METHOD
-  end.join; module_eval(methods)
-
-  # define methods for CSS properties.
-  CSS_PROPERTIES.each do |method_name|
-    define_method method_name do |*args|
-      css_attr = method_name.gsub('_', '-')
-      property(css_attr, args)
-    end
-  end
-
-  # Add a property declaration string to the current selector's properties array.
-  def property(css_attr, *args)
-    @properties[-1] << "#{css_attr}: #{args.join(' ')};"
-  end
-  
-  ##  State transitions
-  
-  # Push the accumulated selector and a new property array onto the
-  # tops of their respected stacks
-  def open_block(new_selector)
-    case @state
-    when :closed_block, :open_block
-      combined_selector = [@selectors[-1], new_selector].compact.join(" ")
-      @selectors.push combined_selector
-      new_property_set
-    when :chain
-      @selectors[-1] = "#{@selectors[-1]}#{new_selector}"
-      new_property_set
-    else
-      raise "You can't get to :open_block from #{@state.inspect}"
-    end
-    
-    @state = :open_block
-  end
-
-  # Pushes accumulated selector on the stack without generating a new properties array.
-  def chain(new_selector)
-    case @state
-    when :closed_block, :open_block
-      combined_selector = [@selectors[-1], new_selector].compact.join(" ")
-      @selectors.push( combined_selector)
-    when :chain
-      @selectors[-1] = "#{@selectors[-1]}#{new_selector}"
-    else
-      raise "You can't get to :chain from #{@state.inspect}"
-    end
-    
-    @state = :chain
-  end
-
-  # Pop the selector string and property array for the closing block
-  # off of their respective stacks
-  def closed_block
-    case @state
-    when :open_block, :closed_block
-      @selectors.pop
-      @properties.pop
-    else
-      raise "You can't get to :closed_block from #{@state.inspect}"
-    end
-    
-    @state = :closed_block
-  end
-
-
-  
-  
-end
-
-Cssy = Cassy = Cassandra
+require 'zlib'
+require 'rubygems'
+require 'thrift'
+
+HERE = File.expand_path(File.dirname(__FILE__))
+
+$LOAD_PATH << "#{HERE}/../vendor/gen-rb"
+require "#{HERE}/../vendor/gen-rb/cassandra"
+
+$LOAD_PATH << "#{HERE}"
+require 'cassandra/array'
+require 'cassandra/time'
+require 'cassandra/comparable'
+require 'cassandra/uuid'
+require 'cassandra/long'
+require 'cassandra/safe_client'
+require 'cassandra/serialization'
+require 'cassandra/ordered_hash'
+require 'cassandra/constants'
+require 'cassandra/helper'
+require 'cassandra/cassandra'