cassandra-mavericks 0.21.1

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"

data/conf/0.7/cassandra.yaml

@@ -0,0 +1,336 @@
+# Cassandra storage config YAML
+
+# NOTE:
+# See http://wiki.apache.org/cassandra/StorageConfiguration for
+# full explanations of configuration directives
+# /NOTE
+
+# The name of the cluster. This is mainly used to prevent machines in
+# one logical cluster from joining another.
+cluster_name: 'Test Cluster'
+
+# You should always specify InitialToken when setting up a production
+# cluster for the first time, and often when adding capacity later.
+# The principle is that each node should be given an equal slice of
+# the token ring; see http://wiki.apache.org/cassandra/Operations
+# for more details.
+#
+# If blank, Cassandra will request a token bisecting the range of
+# the heaviest-loaded existing node. If there is no load information
+# available, such as is the case with a new cluster, it will pick
+# a random token, which will lead to hot spots.
+initial_token:
+
+# Set to true to make new [non-seed] nodes automatically migrate data
+# to themselves from the pre-existing nodes in the cluster. Defaults
+# to false because you can only bootstrap N machines at a time from
+# an existing cluster of N, so if you are bringing up a cluster of
+# 10 machines with 3 seeds you would have to do it in stages. Leaving
+# this off for the initial start simplifies that.
+auto_bootstrap: false
+
+# See http://wiki.apache.org/cassandra/HintedHandoff
+hinted_handoff_enabled: true
+# this defines the maximum amount of time a dead host will have hints
+# generated. After it has been dead this long, hints will be dropped.
+max_hint_window_in_ms: 3600000 # one hour
+# Sleep this long after delivering each row or row fragment
+hinted_handoff_throttle_delay_in_ms: 50
+
+# authentication backend, implementing IAuthenticator; used to identify users
+authenticator: org.apache.cassandra.auth.AllowAllAuthenticator
+
+# authorization backend, implementing IAuthority; used to limit access/provide permissions
+authority: org.apache.cassandra.auth.AllowAllAuthority
+
+# The partitioner is responsible for distributing rows (by key) across
+# nodes in the cluster. 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.ByteOrderedPartitioner,
+# org.apache.cassandra.dht.OrderPreservingPartitioner (deprecated),
+# and org.apache.cassandra.dht.CollatingOrderPreservingPartitioner
+# (deprecated).
+#
+# - RandomPartitioner distributes rows across the cluster evenly by md5.
+# When in doubt, this is the best option.
+# - ByteOrderedPartitioner orders rows lexically by key bytes. BOP allows
+# scanning rows in key order, but the ordering can generate hot spots
+# for sequential insertion workloads.
+# - OrderPreservingPartitioner is an obsolete form of BOP, that stores
+# - keys in a less-efficient format and only works with keys that are
+# UTF8-encoded Strings.
+# - CollatingOPP colates according to EN,US rules rather than lexical byte
+# ordering. Use this as an example if you need custom collation.
+#
+# See http://wiki.apache.org/cassandra/Operations for more on
+# partitioners and token selection.
+partitioner: org.apache.cassandra.dht.RandomPartitioner
+
+# directories where Cassandra should store data on disk.
+data_file_directories:
+    - data/data
+
+# commit log
+commitlog_directory: data/commitlog
+
+# saved caches
+saved_caches_directory: data/saved_caches
+
+# Size to allow commitlog to grow to before creating a new segment
+commitlog_rotation_threshold_in_mb: 128
+
+# commitlog_sync 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.
+commitlog_sync: periodic
+
+# the other option is "periodic" where writes may be acked immediately
+# and the CommitLog is simply synced every commitlog_sync_period_in_ms
+# milliseconds.
+commitlog_sync_period_in_ms: 10000
+
+# emergency pressure valve: each time heap usage after a full (CMS)
+# garbage collection is above this fraction of the max, Cassandra will
+# flush the largest memtables.
+#
+# Set to 1.0 to disable. Setting this lower than
+# CMSInitiatingOccupancyFraction is not likely to be useful.
+#
+# RELYING ON THIS AS YOUR PRIMARY TUNING MECHANISM WILL WORK POORLY:
+# it is most effective under light to moderate load, or read-heavy
+# workloads; under truly massive write load, it will often be too
+# little, too late.
+flush_largest_memtables_at: 0.75
+
+# emergency pressure valve #2: the first time heap usage after a full
+# (CMS) garbage collection is above this fraction of the max,
+# Cassandra will reduce cache maximum _capacity_ to the given fraction
+# of the current _size_. Should usually be set substantially above
+# flush_largest_memtables_at, since that will have less long-term
+# impact on the system.
+#
+# Set to 1.0 to disable. Setting this lower than
+# CMSInitiatingOccupancyFraction is not likely to be useful.
+reduce_cache_sizes_at: 0.85
+reduce_cache_capacity_to: 0.6
+
+# 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:
+    - 127.0.0.1
+
+# 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.)
+disk_access_mode: auto
+
+# For workloads with more data than can fit in memory, Cassandra's
+# bottleneck will be reads that need to fetch data from
+# disk. "concurrent_reads" should be set to (16 * number_of_drives) in
+# order to allow the operations to enqueue low enough in the stack
+# that the OS and drives can reorder them.
+#
+# On the other hand, since writes are almost never IO bound, the ideal
+# number of "concurrent_writes" is dependent on the number of cores in
+# your system; (8 * number_of_cores) is a good rule of thumb.
+concurrent_reads: 32
+concurrent_writes: 32
+
+# This sets the amount of memtable flush writer threads. These will
+# be blocked by disk io, and each one will hold a memtable in memory
+# while blocked. If you have a large heap and many data directories,
+# you can increase this value for better flush performance.
+# By default this will be set to the amount of data directories defined.
+#memtable_flush_writers: 1
+
+# Buffer size to use when performing contiguous column slices.
+# Increase this to the size of the column slices you typically perform
+sliced_buffer_size_in_kb: 64
+
+# TCP port, for commands and data
+storage_port: 7000
+
+# Address to bind to and tell other Cassandra 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).
+#
+# Setting this to 0.0.0.0 is always wrong.
+listen_address: localhost
+
+# The address to bind the Thrift RPC service to -- clients connect
+# here. 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).
+rpc_address: localhost
+# port for Thrift to listen for clients on
+rpc_port: 9160
+
+# enable or disable keepalive on rpc connections
+rpc_keepalive: true
+
+# Cassandra uses thread-per-client for client RPC. This can
+# be expensive in memory used for thread stack for a large
+# enough number of clients. (Hence, connection pooling is
+# very, very strongly recommended.)
+#
+# Uncomment rpc_min|max|thread to set request pool size.
+# You would primarily set max as a safeguard against misbehaved
+# clients; if you do hit the max, Cassandra will block until
+# one disconnects before accepting more. The defaults are
+# min of 16 and max unlimited.
+#
+# rpc_min_threads: 16
+# rpc_max_threads: 2048
+
+# uncomment to set socket buffer sizes on rpc connections
+# rpc_send_buff_size_in_bytes:
+# rpc_recv_buff_size_in_bytes:
+
+# Frame size for thrift (maximum field length).
+# 0 disables TFramedTransport in favor of TSocket. This option
+# is deprecated; we strongly recommend using Framed mode.
+thrift_framed_transport_size_in_mb: 15
+
+# The max length of a thrift message, including all fields and
+# internal thrift overhead.
+thrift_max_message_length_in_mb: 16
+
+# Set to true to have Cassandra create a hard link to each sstable
+# flushed or streamed locally in a backups/ subdirectory of the
+# Keyspace data. Removing these links is the operator's
+# responsibility.
+incremental_backups: false
+
+# Whether or not to take a snapshot before each compaction. Be
+# careful using this option, since Cassandra won't clean up the
+# snapshots for you. Mostly useful if you're paranoid when there
+# is a data format change.
+snapshot_before_compaction: false
+
+# change this to increase the compaction thread's priority. In java, 1 is the
+# lowest priority and that is our default.
+# compaction_thread_priority: 1
+
+# 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.
+column_index_size_in_kb: 64
+
+# Size limit for rows being compacted in memory. Larger rows will spill
+# over to disk and use a slower two-pass compaction process. A message
+# will be logged specifying the row key.
+in_memory_compaction_limit_in_mb: 64
+
+# Track cached row keys during compaction, and re-cache their new
+# positions in the compacted sstable. Disable if you use really large
+# key caches.
+compaction_preheat_key_cache: true
+
+# Time to wait for a reply from other nodes before failing the command
+rpc_timeout_in_ms: 10000
+
+# phi value that must be reached for a host to be marked down.
+# most users should never need to adjust this.
+# phi_convict_threshold: 8
+
+# endpoint_snitch -- Set this to a class that implements
+# IEndpointSnitch, which will let Cassandra know enough
+# about your network topology to route requests efficiently.
+# Out of the box, Cassandra provides
+# - org.apache.cassandra.locator.SimpleSnitch:
+# Treats Strategy order as proximity. This improves cache locality
+# when disabling read repair, which can further improve throughput.
+# - org.apache.cassandra.locator.RackInferringSnitch:
+# Proximity is determined by rack and data center, which are
+# assumed to correspond to the 3rd and 2nd octet of each node's
+# IP address, respectively
+# org.apache.cassandra.locator.PropertyFileSnitch:
+# - Proximity is determined by rack and data center, which are
+# explicitly configured in cassandra-topology.properties.
+endpoint_snitch: org.apache.cassandra.locator.SimpleSnitch
+
+# dynamic_snitch -- This boolean controls whether the above snitch is
+# wrapped with a dynamic snitch, which will monitor read latencies
+# and avoid reading from hosts that have slowed (due to compaction,
+# for instance)
+dynamic_snitch: true
+# controls how often to perform the more expensive part of host score
+# calculation
+dynamic_snitch_update_interval_in_ms: 100
+# controls how often to reset all host scores, allowing a bad host to
+# possibly recover
+dynamic_snitch_reset_interval_in_ms: 600000
+# if set greater than zero and read_repair_chance is < 1.0, this will allow
+# 'pinning' of replicas to hosts in order to increase cache capacity.
+# The badness threshold will control how much worse the pinned host has to be
+# before the dynamic snitch will prefer other replicas over it. This is
+# expressed as a double which represents a percentage. Thus, a value of
+# 0.2 means Cassandra would continue to prefer the static snitch values
+# until the pinned host was 20% worse than the fastest.
+dynamic_snitch_badness_threshold: 0.0
+
+# request_scheduler -- Set this to a class that implements
+# RequestScheduler, which will schedule incoming client requests
+# according to the specific policy. This is useful for multi-tenancy
+# with a single Cassandra cluster.
+# NOTE: This is specifically for requests from the client and does
+# not affect inter node communication.
+# org.apache.cassandra.scheduler.NoScheduler - No scheduling takes place
+# org.apache.cassandra.scheduler.RoundRobinScheduler - Round robin of
+# client requests to a node with a separate queue for each
+# request_scheduler_id. The scheduler is further customized by
+# request_scheduler_options as described below.
+request_scheduler: org.apache.cassandra.scheduler.NoScheduler
+
+# Scheduler Options vary based on the type of scheduler
+# NoScheduler - Has no options
+# RoundRobin
+# - throttle_limit -- The throttle_limit is the number of in-flight
+# requests per client. Requests beyond
+# that limit are queued up until
+# running requests can complete.
+# The value of 80 here is twice the number of
+# concurrent_reads + concurrent_writes.
+# - default_weight -- default_weight is optional and allows for
+# overriding the default which is 1.
+# - weights -- Weights are optional and will default to 1 or the
+# overridden default_weight. The weight translates into how
+# many requests are handled during each turn of the
+# RoundRobin, based on the scheduler id.
+#
+# request_scheduler_options:
+# throttle_limit: 80
+# default_weight: 5
+# weights:
+# Keyspace1: 1
+# Keyspace2: 5
+
+# request_scheduler_id -- An identifer based on which to perform
+# the request scheduling. Currently the only valid option is keyspace.
+# request_scheduler_id: keyspace
+
+# The Index Interval determines how large the sampling of row keys
+# is for a given SSTable. The larger the sampling, the more effective
+# the index is at the cost of space.
+index_interval: 128

data/conf/0.7/log4j-server.properties

@@ -0,0 +1,41 @@
+# 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 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.PatternLayout
+log4j.appender.stdout.layout.ConversionPattern=%5p %d{HH:mm:ss,SSS} %m%n
+
+# rolling log file
+log4j.appender.R=org.apache.log4j.RollingFileAppender
+log4j.appender.R.maxFileSize=20MB
+log4j.appender.R.maxBackupIndex=50
+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.org.apache.cassandra=DEBUG
+#log4j.logger.org.apache.cassandra.db=DEBUG
+#log4j.logger.org.apache.cassandra.service.StorageProxy=DEBUG
+

data/conf/0.7/schema.json

@@ -0,0 +1,57 @@
+{"Twitter":{
+    "Users":{
+      "comparator_type":"org.apache.cassandra.db.marshal.UTF8Type",
+      "column_type":"Standard"},
+    "UserAudits":{
+      "comparator_type":"org.apache.cassandra.db.marshal.UTF8Type",
+      "column_type":"Standard"},
+    "UserRelationships":{ 
+      "subcomparator_type":"org.apache.cassandra.db.marshal.TimeUUIDType",
+      "comparator_type":"org.apache.cassandra.db.marshal.UTF8Type",
+      "column_type":"Super"},
+    "Usernames":{
+      "comparator_type":"org.apache.cassandra.db.marshal.UTF8Type",
+      "column_type":"Standard"},
+    "Statuses":{
+      "comparator_type":"org.apache.cassandra.db.marshal.UTF8Type",
+      "column_type":"Standard"},
+    "StatusAudits":{
+      "comparator_type":"org.apache.cassandra.db.marshal.UTF8Type",
+      "column_type":"Standard"},
+    "StatusRelationships":{
+      "subcomparator_type":"org.apache.cassandra.db.marshal.TimeUUIDType",
+      "comparator_type":"org.apache.cassandra.db.marshal.UTF8Type",
+      "column_type":"Super"},
+    "Indexes":{
+      "comparator_type":"org.apache.cassandra.db.marshal.UTF8Type",
+      "column_type":"Super"},
+    "TimelinishThings":{
+      "comparator_type":"org.apache.cassandra.db.marshal.BytesType",
+      "column_type":"Standard"}
+  },
+"Multiblog":{
+    "Blogs":{
+      "comparator_type":"org.apache.cassandra.db.marshal.TimeUUIDType",
+      "column_type":"Standard"},
+    "Comments":{
+      "comparator_type":"org.apache.cassandra.db.marshal.TimeUUIDType",
+      "column_type":"Standard"}
+  },
+"MultiblogLong":{
+    "Blogs":{
+      "comparator_type":"org.apache.cassandra.db.marshal.LongType",
+      "column_type":"Standard"},
+    "Comments":{
+      "comparator_type":"org.apache.cassandra.db.marshal.LongType",
+      "column_type":"Standard"}
+  },
+"TypeConversions":{
+    "UUIDColumnConversion":{
+      "comparator_type":"org.apache.cassandra.db.marshal.TimeUUIDType",
+      "column_type":"Standard"},
+    "SuperUUID":{
+      "subcomparator_type":"org.apache.cassandra.db.marshal.TimeUUIDType",
+      "comparator_type":"org.apache.cassandra.db.marshal.TimeUUIDType",
+      "column_type":"Super"}
+  }
+}