mcmire-cassandra 0.12.2

data/conf/0.6/storage-conf.xml

@@ -0,0 +1,352 @@
+<!--
+ ~ 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                                                  -->
+  <!--======================================================================-->
+
+  <!-- 
+   ~ The name of this cluster.  This is mainly used to prevent machines in
+   ~ one logical cluster from joining another.
+  -->
+  <ClusterName>Test</ClusterName>
+
+  <!--
+   ~ Turn on to make new [non-seed] nodes automatically migrate the right data 
+   ~ to themselves.  (If no InitialToken is specified, they will pick one 
+   ~ such that they will get half the range of the most-loaded node.)
+   ~ If a node starts up without bootstrapping, it will mark itself bootstrapped
+   ~ so that you can't subsequently accidently bootstrap a node with
+   ~ data on it.  (You can reset this by wiping your data and commitlog
+   ~ directories.)
+   ~
+   ~ Off by default so that new clusters and upgraders from 0.4 don't
+   ~ bootstrap immediately.  You should turn this on when you start adding
+   ~ new nodes to a cluster that already has data on it.  (If you are upgrading
+   ~ from 0.4, start your cluster with it off once before changing it to true.
+   ~ Otherwise, no data will be lost but you will incur a lot of unnecessary
+   ~ I/O before your cluster starts up.)
+  -->
+  <AutoBootstrap>false</AutoBootstrap>
+
+  <!--
+   ~ Keyspaces and ColumnFamilies:
+   ~ A ColumnFamily is the Cassandra concept closest to a relational
+   ~ table.  Keyspaces are separate groups of ColumnFamilies.  Except in
+   ~ very unusual circumstances you will have one Keyspace per application.
+
+   ~ There is an implicit keyspace named 'system' for Cassandra internals.
+  -->
+  <Keyspaces>
+    <Keyspace Name="Twitter">
+        <KeysCachedFraction>0.01</KeysCachedFraction>
+        <ColumnFamily CompareWith="UTF8Type" Name="Users" />
+        <ColumnFamily CompareWith="UTF8Type" Name="UserAudits" />
+        <ColumnFamily CompareWith="UTF8Type" CompareSubcolumnsWith="TimeUUIDType" ColumnType="Super" Name="UserRelationships" />
+        <ColumnFamily CompareWith="UTF8Type" Name="Usernames" />
+        <ColumnFamily CompareWith="UTF8Type" Name="Statuses" />
+        <ColumnFamily CompareWith="UTF8Type" Name="StatusAudits" />
+        <ColumnFamily CompareWith="UTF8Type" CompareSubcolumnsWith="TimeUUIDType" ColumnType="Super" Name="StatusRelationships" />  
+        <ColumnFamily CompareWith="UTF8Type" ColumnType="Super" Name="Index" />
+        <ColumnFamily CompareWith="BytesType" ColumnType="Standard" Name="TimelinishThings" />
+
+        <ReplicaPlacementStrategy>org.apache.cassandra.locator.RackUnawareStrategy</ReplicaPlacementStrategy>
+        <ReplicationFactor>1</ReplicationFactor>
+        <EndPointSnitch>org.apache.cassandra.locator.EndPointSnitch</EndPointSnitch>
+    </Keyspace>
+
+    <Keyspace Name="Multiblog">      
+      <KeysCachedFraction>0.01</KeysCachedFraction>
+      <ColumnFamily CompareWith="TimeUUIDType" Name="Blogs"/>
+      <ColumnFamily CompareWith="TimeUUIDType" Name="Comments"/>
+
+      <ReplicaPlacementStrategy>org.apache.cassandra.locator.RackUnawareStrategy</ReplicaPlacementStrategy>
+      <ReplicationFactor>1</ReplicationFactor>
+      <EndPointSnitch>org.apache.cassandra.locator.EndPointSnitch</EndPointSnitch>
+    </Keyspace>
+
+    <Keyspace Name="MultiblogLong">
+      <KeysCachedFraction>0.01</KeysCachedFraction>
+      <ColumnFamily CompareWith="LongType" Name="Blogs"/>
+      <ColumnFamily CompareWith="LongType" Name="Comments"/>
+
+      <ReplicaPlacementStrategy>org.apache.cassandra.locator.RackUnawareStrategy</ReplicaPlacementStrategy>
+      <ReplicationFactor>1</ReplicationFactor>
+      <EndPointSnitch>org.apache.cassandra.locator.EndPointSnitch</EndPointSnitch>
+    </Keyspace>
+
+    <Keyspace Name="TypeConversions">
+      <KeysCachedFraction>0.01</KeysCachedFraction>
+      <ColumnFamily CompareWith="TimeUUIDType" Name="UUIDColumnConversion"/>
+      <ColumnFamily CompareWith="TimeUUIDType" CompareSubcolumnsWith="UTF8Type" ColumnType="Super" Name="SuperUUID"/>
+
+      <ReplicaPlacementStrategy>org.apache.cassandra.locator.RackUnawareStrategy</ReplicaPlacementStrategy>
+      <ReplicationFactor>1</ReplicationFactor>
+      <EndPointSnitch>org.apache.cassandra.locator.EndPointSnitch</EndPointSnitch>
+    </Keyspace>
+
+    <Keyspace Name="CassandraObject">
+      <KeysCachedFraction>0.01</KeysCachedFraction>
+      <ColumnFamily CompareWith="UTF8Type" Name="Customers" />
+      <ColumnFamily CompareWith="UTF8Type" CompareSubcolumnsWith="TimeUUIDType" ColumnType="Super" Name="CustomerRelationships" />
+      <ColumnFamily CompareWith="TimeUUIDType" Name="CustomersByLastName" />
+      <ColumnFamily CompareWith="UTF8Type" Name="Invoices" />
+      <ColumnFamily CompareWith="UTF8Type" CompareSubcolumnsWith="TimeUUIDType" ColumnType="Super" Name="InvoiceRelationships" />
+      <ColumnFamily CompareWith="UTF8Type" Name="InvoicesByNumber" />
+      <ColumnFamily CompareWith="UTF8Type" Name="Payments" />
+      <ColumnFamily CompareWith="UTF8Type" Name="Appointments" />
+      <!-- <ColumnFamily CompareWith="UTF8Type" Name="FirstNames" /> -->
+
+      <ReplicaPlacementStrategy>org.apache.cassandra.locator.RackUnawareStrategy</ReplicaPlacementStrategy>
+      <ReplicationFactor>1</ReplicationFactor>
+      <EndPointSnitch>org.apache.cassandra.locator.EndPointSnitch</EndPointSnitch>
+    </Keyspace>
+  </Keyspaces>
+
+  <!--
+   ~ Authenticator: any IAuthenticator may be used, including your own as long
+   ~ as it is on the classpath.  Out of the box, Cassandra provides
+   ~ org.apache.cassandra.auth.AllowAllAuthenticator and,
+   ~ org.apache.cassandra.auth.SimpleAuthenticator 
+   ~ (SimpleAuthenticator uses access.properties and passwd.properties by
+   ~ default).
+   ~
+   ~ If you don't specify an authenticator, AllowAllAuthenticator is used.
+  -->
+  <Authenticator>org.apache.cassandra.auth.AllowAllAuthenticator</Authenticator>
+
+  <!--
+   ~ 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,
+   ~ org.apache.cassandra.dht.OrderPreservingPartitioner, and
+   ~ org.apache.cassandra.dht.CollatingOrderPreservingPartitioner.
+   ~ (CollatingOPP colates according to EN,US rules, not naive byte
+   ~ ordering.  Use this as an example if you need locale-aware collation.)
+   ~ Range queries require using an order-preserving partitioner.
+   ~
+   ~ Achtung!  Changing this parameter requires wiping your data
+   ~ directories, since the partitioner can modify the sstable on-disk
+   ~ format.
+  -->
+  <Partitioner>org.apache.cassandra.dht.RandomPartitioner</Partitioner>
+
+  <!--
+   ~ If you are using an order-preserving partitioner 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>
+
+  <!--
+   ~ 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>
+  <StagingFileDirectory>data/staging</StagingFileDirectory>
+  <SavedCachesDirectory>data/saved_caches</SavedCachesDirectory>
+
+
+  <!--
+   ~ Addresses 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. You must change this if you are running multiple nodes!
+  -->
+  <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>
+  <!-- internal communications port -->
+  <StoragePort>7000</StoragePort>
+
+  <!--
+   ~ 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>
+  <!-- 
+   ~ Whether or not to use a framed transport for Thrift. If this option
+   ~ is set to true then you must also use a framed transport on the 
+   ~ client-side, (framed and non-framed transports are not compatible).
+  -->
+  <ThriftFramedTransport>false</ThriftFramedTransport>
+
+
+  <!--======================================================================-->
+  <!-- Memory, Disk, and Performance                                        -->
+  <!--======================================================================-->
+
+  <!--
+   ~ Access mode.  mmapped i/o is substantially faster, but only practical on
+   ~ a 64bit machine (which notably does not include EC2 "small" instances)
+   ~ or relatively small datasets.  "auto", the safe choice, will enable
+   ~ mmapping on a 64bit JVM.  Other values are "mmap", "mmap_index_only"
+   ~ (which may allow you to get part of the benefits of mmap on a 32bit
+   ~ machine by mmapping only index files) and "standard".
+   ~ (The buffer size settings that follow only apply to standard,
+   ~ non-mmapped i/o.)
+   -->
+  <DiskAccessMode>auto</DiskAccessMode>
+
+  <!--
+   ~ Buffer size to use when performing contiguous column slices. Increase
+   ~ this to the size of the column slices you typically perform. 
+   ~ (Name-based queries are performed with a buffer size of 
+   ~ ColumnIndexSizeInKB.)
+  -->
+  <SlicedBufferSizeInKB>64</SlicedBufferSizeInKB>
+
+  <!--
+   ~ Buffer size to use when flushing memtables to disk. (Only one 
+   ~ memtable is ever flushed at a time.) Increase (decrease) the index
+   ~ buffer size relative to the data buffer if you have few (many) 
+   ~ columns per key.  Bigger is only better _if_ your memtables get large
+   ~ enough to use the space. (Check in your data directory after your
+   ~ app has been running long enough.) -->
+  <FlushDataBufferSizeInMB>32</FlushDataBufferSizeInMB>
+  <FlushIndexBufferSizeInMB>8</FlushIndexBufferSizeInMB>
+
+  <!--
+   ~ Add column indexes to a row after its contents reach this size.
+   ~ Increase if your column values are large, or if you have a very large
+   ~ number of columns.  The competing causes are, Cassandra has to
+   ~ deserialize this much of the row to read a single column, so you want
+   ~ it to be small - at least if you do many partial-row reads - but all
+   ~ the index data is read for each access, so you don't want to generate
+   ~ that wastefully either.
+  -->
+  <ColumnIndexSizeInKB>64</ColumnIndexSizeInKB>
+
+  <!--
+   ~ Flush memtable after this much data has been inserted, including
+   ~ overwritten data.  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).
+  -->
+  <MemtableThroughputInMB>64</MemtableThroughputInMB>
+  <!--
+   ~ Throughput setting for Binary Memtables.  Typically these are
+   ~ used for bulk load so you want them to be larger.
+  -->
+  <BinaryMemtableThroughputInMB>256</BinaryMemtableThroughputInMB>
+  <!--
+   ~ The maximum number of columns in millions to store in memory per
+   ~ ColumnFamily before flushing to disk.  This is also a per-memtable
+   ~ setting.  Use with MemtableThroughputInMB to tune memory usage.
+  -->
+  <MemtableOperationsInMillions>0.3</MemtableOperationsInMillions>
+  <!--
+   ~ The maximum time to leave a dirty memtable unflushed.
+   ~ (While any affected columnfamilies have unflushed data from a
+   ~ commit log segment, that segment cannot be deleted.)
+   ~ This needs to be large enough that it won't cause a flush storm
+   ~ of all your memtables flushing at once because none has hit
+   ~ the size or count thresholds yet.  For production, a larger
+   ~ value such as 1440 is recommended.
+  -->
+  <MemtableFlushAfterMinutes>60</MemtableFlushAfterMinutes>
+
+  <!--
+   ~ 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.  Increase ConcurrentWrites to
+   ~ the number of clients writing at once if you enable CommitLogSync +
+   ~ CommitLogSyncDelay. -->
+  <ConcurrentReads>8</ConcurrentReads>
+  <ConcurrentWrites>32</ConcurrentWrites>
+
+  <!--
+   ~ CommitLogSync may be either "periodic" or "batch."  When in batch
+   ~ mode, Cassandra won't ack writes until the commit log has been
+   ~ fsynced to disk.  It will wait up to CommitLogSyncBatchWindowInMS
+   ~ milliseconds for other writes, before performing the sync.
+
+   ~ 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.
+   ~ So the other option is "timed," where writes may be acked immediately
+   ~ and the CommitLog is simply synced every CommitLogSyncPeriodInMS
+   ~ milliseconds.
+  -->
+  <CommitLogSync>periodic</CommitLogSync>
+  <!--
+   ~ Interval at which to perform syncs of the CommitLog in periodic mode.
+   ~ Usually the default of 10000ms is fine; increase it if your i/o
+   ~ load is such that syncs are taking excessively long times.
+  -->
+  <CommitLogSyncPeriodInMS>10000</CommitLogSyncPeriodInMS>
+  <!--
+   ~ Delay (in milliseconds) during which additional commit log entries
+   ~ may be written before fsync in batch mode.  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 0.1 to 10 or
+   ~ even more if throughput matters more than latency.
+  -->
+  <!-- <CommitLogSyncBatchWindowInMS>1</CommitLogSyncBatchWindowInMS> --> 
+
+  <!--
+   ~ 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/conf/0.7/cassandra.in.sh

@@ -0,0 +1,46 @@
+# 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.
+
+if [ "x$CASSANDRA_HOME" = "x" ]; then
+  CASSANDRA_HOME=`dirname $0`/..
+fi
+
+# The directory where Cassandra's configs live (required)
+if [ "x$CASSANDRA_CONF" = "x" ]; then
+  CASSANDRA_CONF=$CASSANDRA_HOME/conf
+fi
+
+# This can be the path to a jar file, or a directory containing the
+# compiled classes. NOTE: This isn't needed by the startup script,
+# it's just used here in constructing the classpath.
+cassandra_bin=$CASSANDRA_HOME/build/classes
+#cassandra_bin=$cassandra_home/build/cassandra.jar
+
+# JAVA_HOME can optionally be set here
+#JAVA_HOME=/usr/local/jdk6
+
+# The java classpath (required)
+CLASSPATH=$CASSANDRA_CONF:$cassandra_bin
+
+for jar in $CASSANDRA_HOME/lib/*.jar; do
+  CLASSPATH=$CLASSPATH:$jar
+done
+
+# Arguments to pass to the JVM
+JVM_OPTS=" \
+        -ea \
+        -Xms128M \
+        -Xmx1G"