rubber-jcarnegie 0.0.1

data/generators/vulcanize/templates/base/lib/tasks/rubber.rake

@@ -0,0 +1,15 @@
+# rails tries to load this from generator dir, so skip it.
+if __FILE__ !~ /rubber\/generators\/vulcanize/
+
+  env = ENV['RUBBER_ENV'] ||= (ENV['RAILS_ENV'] || 'development')
+  root = File.dirname(__FILE__) + '/../..'
+
+  # this tries first as a rails plugin then as a gem
+  $:.unshift "#{root}/vendor/plugins/rubber/lib/"
+  require 'rubber'
+
+  Rubber::initialize(root, env)
+
+  require 'rubber/tasks/rubber'
+
+end

data/generators/vulcanize/templates/base/script/cron-rake

@@ -0,0 +1,18 @@
+#!/usr/bin/env ruby
+
+# For running rake jobs through cron - only prints output if there is an error
+#
+# author mconway
+# since 8/12/07
+
+RAILS_ROOT = File.expand_path("..", File.dirname(__FILE__))
+log = "#{RAILS_ROOT}/log/cron-rake-#{Time.now.tv_sec}.log"
+begin
+  ident = File.basename(ARGV[-1]).gsub(/\W+/, "_")
+  log = "#{RAILS_ROOT}/log/cron-rake-#{ident}.log"
+rescue
+end
+
+Dir.chdir(RAILS_ROOT)
+args = %W{-l #{log} -- rake --trace} + ARGV
+system "script/cron-sh", *args

data/generators/vulcanize/templates/base/script/cron-runner

@@ -0,0 +1,18 @@
+#!/usr/bin/env ruby
+
+# For running jobs through cron - only prints output if there is an error
+#
+# author mconway
+# since 8/12/07
+
+RAILS_ROOT = File.expand_path("..", File.dirname(__FILE__))
+log = "#{RAILS_ROOT}/log/cron-runner-#{Time.now.tv_sec}.log"
+begin
+  ident = File.basename(ARGV[-1]).gsub(/\W+/, "_")
+  log = "#{RAILS_ROOT}/log/cron-runner-#{ident}.log"
+rescue
+end
+
+Dir.chdir(RAILS_ROOT)
+args = %W{-e -l #{log} -- RAILS_RUNNER} + ARGV
+system "script/cron-sh", *args

data/generators/vulcanize/templates/base/script/cron-sh

@@ -0,0 +1,67 @@
+#!/usr/bin/env ruby
+
+# For running shell commands through cron - only prints output if there is an error
+#
+# author mconway
+# since 8/12/07
+
+require 'optparse'
+require 'ostruct'
+require 'rubygems'
+require 'open4'
+
+options = OpenStruct.new
+options.logfile = "/tmp/cron-sh-#{Time.now.tv_sec}.log"
+options.echoerr = false
+options.echoout = false
+
+opts = OptionParser.new do |opts|
+  opts.banner = "Usage: cron-sh [options] <shell command>"
+  opts.separator "Runs the given command, sending all stdout/stderr to a logfile, but echoing"
+  opts.separator "the entire file if the command exits with an error"
+  opts.separator ""
+  opts.separator "Specific options:"
+
+  opts.on("-l", "--log logfile", "Log to given file instead of a default") do |val|
+    options.logfile = val
+  end
+
+  opts.on("-o", "--[no-]echoout", "Log _and_ echo stdout") do |val|
+    options.echoout = true
+  end
+
+  opts.on("-e", "--[no-]echoerr", "Log _and_ echo stderr") do |val|
+    options.echoerr = true
+  end
+
+  opts.on_tail("-h", "--help", "Show this message") do
+    puts opts
+    exit
+  end
+end
+
+cmd = opts.parse(ARGV)
+
+status = Open4::popen4(*cmd) do |pid, stdin, stdout, stderr|
+  File.open(options.logfile, "w") do | fh |
+    threads = []
+    threads <<  Thread.new(stdout) do |stdout|
+       stdout.each { |line| $stdout.puts line if options.echoout; fh.print line; fh.flush }
+    end
+    threads <<  Thread.new(stderr) do |stderr|
+       stderr.each { |line| $stderr.puts line if options.echoerr; fh.print line; fh.flush }
+    end
+    threads.each { |t| t.join }
+  end
+end
+
+result = status.exitstatus
+if result != 0
+  puts ""
+  puts "*** Process exited with non-zero error code, full output follows"
+  puts "*** Command was: #{cmd.join(' ')}"
+  puts ""
+  puts IO.read(options.logfile)
+end
+
+exit(result)

data/generators/vulcanize/templates/base/templates.rb

@@ -0,0 +1,11 @@
+gem "rubber", Rubber.version if Rubber::Util::is_bundler? && ! Rubber::Util::rubber_as_plugin?
+
+if Rubber::Util::is_rails2?
+  m.gsub_file('script/cron-runner', /RAILS_RUNNER/, 'script/runner')
+  m.gsub_file('Rakefile', /RAILS_LOADER/, "require(File.join(File.dirname(__FILE__), 'config', 'boot'))")
+  m.gsub_file('Rakefile', /RAILS_TASKS/, "require 'tasks/rails'")
+else
+  gsub_file('script/cron-runner', /RAILS_RUNNER/, 'rails runner')
+  gsub_file('Rakefile', /RAILS_LOADER/, '')
+  gsub_file('Rakefile', /RAILS_TASKS/, '')
+end

data/generators/vulcanize/templates/base/templates.yml

@@ -0,0 +1,6 @@
+description: The core configuration needed by all others
+
+# only include Rakefile when generating for non-rails apps, as we use rails
+# rake loading mechanism for including rakefile in rails apps
+optional:
+  Rakefile: "!rails?"

data/generators/vulcanize/templates/cassandra/config/rubber/deploy-cassandra.rb

@@ -0,0 +1,88 @@
+
+namespace :rubber do
+
+  namespace :cassandra do
+  
+    rubber.allow_optional_tasks(self)
+  
+    after "rubber:install_packages", "rubber:cassandra:install"
+    
+    task :install, :roles => :cassandra do
+      rubber.sudo_script 'install_cassandra', <<-ENDSCRIPT
+        if [[ ! -d "#{rubber_env.cassandra_dir}" ]]; then
+          wget -qNP /tmp #{rubber_env.cassandra_pkg_url}
+          tar -C #{rubber_env.cassandra_prefix} -zxf /tmp/apache-cassandra-#{rubber_env.cassandra_version}-bin.tar.gz
+          wget -qNO #{rubber_env.cassandra_dir}/jmxterm.jar http://downloads.sourceforge.net/project/cyclops-group/jmxterm/1.0-alpha-4/jmxterm-1.0-alpha-4-uber.jar
+        fi
+      ENDSCRIPT
+    end
+
+    after "rubber:bootstrap", "rubber:cassandra:bootstrap"
+
+    task :bootstrap, :roles => :cassandra do
+      instances = rubber_instances.for_role("cassandra") & rubber_instances.filtered
+      instances.each do |ic|
+        task_name = "_bootstrap_cassandra_#{ic.full_name}".to_sym()
+        task task_name, :hosts => ic.full_name do
+          env = rubber_cfg.environment.bind("cassandra", ic.name)
+          exists = capture("echo $(ls #{env.cassandra_data_dir}/ 2> /dev/null)")
+          if exists.strip.size == 0
+            # After everything installed on machines, we need the source tree
+            # on hosts in order to run rubber:config for bootstrapping the db
+            deploy.update_code
+
+            # Gen just the conf for cassandra
+            rubber.run_config(:RUBBER_ENV => RUBBER_ENV, :FILE => "role/cassandra", :FORCE => true, :deploy_path => release_path)
+
+            cassandra_start
+            
+            # temporary hack to load initial schema from cassandra.yaml until
+            # something better available.  Subsequent schema changes should be
+            # done using thrift system_* api
+            # http://wiki.apache.org/cassandra/FAQ#no_keyspaces
+            # http://wiki.apache.org/cassandra/LiveSchemaUpdates
+            if instances.size == 1
+              rubber.sudo_script "install_cassandra_schema", <<-ENDSCRIPT
+                echo run -b org.apache.cassandra.service:type=StorageService loadSchemaFromYAML |\
+                  java -jar #{rubber_env.cassandra_dir}/jmxterm.jar -n -l #{ic.full_name}:#{rubber_env.cassandra_jmx_port}
+              ENDSCRIPT
+            end
+          end
+        end
+        send task_name
+      end
+    end
+    
+    on :load do
+      rubber.serial_task self, :serial_restart, :roles => :cassandra do
+        cassandra_stop
+        cassandra_start
+      end
+
+      rubber.serial_task self, :serial_reload, :roles => :cassandra do
+      end
+    end
+
+    def cassandra_stop
+      rsudo "pid=`cat #{rubber_env.cassandra_pid_file}` && kill $pid; while ps $pid &> /dev/null; do sleep 1; done"
+    end
+
+    def cassandra_start
+      rsudo "nohup #{rubber_env.cassandra_dir}/bin/cassandra -p #{rubber_env.cassandra_pid_file} &> #{rubber_env.cassandra_log_dir}/startup.log"
+    end
+
+    task :restart, :roles => :cassandra do
+      rubber.cassandra.stop
+      rubber.cassandra.start
+    end
+    
+    task :stop, :roles => :cassandra do
+      cassandra_stop
+    end
+    
+    task :start, :roles => :cassandra do
+      cassandra_start
+    end
+    
+  end
+end

data/generators/vulcanize/templates/cassandra/config/rubber/role/cassandra/cassandra.in.sh

@@ -0,0 +1,60 @@
+<%
+  @path = "#{rubber_env.cassandra_dir}/bin/cassandra.in.sh"
+%>
+
+# 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=`dirname $0`/..
+
+# The directory where Cassandra's configs live (required)
+CASSANDRA_CONF=$cassandra_home/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
+
+# 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 \
+        -XX:TargetSurvivorRatio=90 \
+        -XX:+AggressiveOpts \
+        -XX:+UseParNewGC \
+        -XX:+UseConcMarkSweepGC \
+        -XX:+CMSParallelRemarkEnabled \
+        -XX:+HeapDumpOnOutOfMemoryError \
+        -XX:SurvivorRatio=128 \
+        -XX:MaxTenuringThreshold=0 \
+        -Dcom.sun.management.jmxremote.port=<%= rubber_env.cassandra_jmx_port %> \
+        -Dcom.sun.management.jmxremote.ssl=false \
+        -Dcom.sun.management.jmxremote.authenticate=false"
+
+ulimit -n 65536

data/generators/vulcanize/templates/cassandra/config/rubber/role/cassandra/cassandra.yaml

@@ -0,0 +1,210 @@
+<%
+  @path = "#{rubber_env.cassandra_dir}/conf/cassandra.yaml"
+  @post = "mkdir -p #{rubber_env.cassandra_data_dir} #{rubber_env.cassandra_commitlog_dir} #{rubber_env.cassandra_log_dir}"
+%>
+# Cassandra storage config YAML
+# See http://wiki.apache.org/cassandra/StorageConfiguration for
+# explanations of configuration directives.
+
+# name of the cluster
+cluster_name: '<%= rubber_env.app_name %>_<%= Rubber.env %>_cluster'
+
+# Set to true to make new [non-seed] nodes automatically migrate the
+# right data to themselves.
+auto_bootstrap: <%= rubber_instances.for_role("cassandra").size > 1 ? "true" : "false" %>
+
+# authentication backend, implementing IAuthenticator; used to limit keyspace access
+authenticator: org.apache.cassandra.auth.AllowAllAuthenticator
+
+# 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.
+partitioner: org.apache.cassandra.dht.RandomPartitioner
+
+# directories where Cassandra should store data on disk.
+data_file_directories:
+    - <%= rubber_env.cassandra_data_dir %>
+
+# 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 = rubber_instances.for_role('cassandra_seed')
+  seeds = rubber_instances.for_role('cassandra') if seeds.size == 0
+  seed_hosts = seeds.collect { |i| i.full_name }
+%>
+seeds:
+    <% seed_hosts.each do |host| %>
+      - <%= host %>
+    <% end %>
+
+# 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
+
+# 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. -->
+concurrent_reads: 8
+concurrent_writes: 32
+
+# 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: <%= rubber_env.cassandra_storage_port %>
+
+# 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!
+listen_address: <%= rubber_env.full_host %>
+
+# The address to bind the Thrift RPC service to
+rpc_address: <%= rubber_env.full_host %>
+# port for Thrift to listen on
+rpc_port: <%= rubber_env.cassandra_rpc_port %>
+# Whether or not to use a framed transport for Thrift.
+thrift_framed_transport: false
+snapshot_before_compaction: false
+
+# The threshold size in megabytes the binary memtable must grow to,
+# before it's submitted for flushing to disk.
+binary_memtable_throughput_in_mb: 256
+# Number of minutes to keep a memtable in memory
+memtable_flush_after_mins: 60
+# Size of the memtable in memory before it is dumped
+memtable_throughput_in_mb: 64
+# Number of objects in millions in the memtable before it is dumped
+memtable_operations_in_millions: 0.3
+# Buffer size to use when flushing !memtables to disk.
+flush_data_buffer_size_in_mb: 32
+# Increase (decrease) the index buffer size relative to the data
+# buffer if you have few (many) columns per key.
+flush_index_buffer_size_in_mb: 8
+
+column_index_size_in_kb: 64
+row_warning_threshold_in_mb: 512
+
+# commit log
+commitlog_directory: <%= rubber_env.cassandra_commitlog_dir %>
+
+# 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 "timed," 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
+
+# Time to wait for a reply from other nodes before failing the command
+rpc_timeout_in_ms: 10000
+
+# time to wait before garbage collecting tombstones (deletion markers)
+gc_grace_seconds: 864000
+
+# 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,
+# org.apache.cassandra.locator.RackInferringSnitch, and
+# org.apache.cassandra.locator.PropertyFileSnitch.
+endpoint_snitch: org.apache.cassandra.locator.SimpleSnitch
+
+# 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.
+#
+# Keyspace required parameters:
+# - name: name of the keyspace; "system" and "definitions" are
+#   reserved for Cassandra Internals.
+# - replica_placement_strategy: the class that determines how replicas
+#   are distributed among nodes.  Must implement IReplicaPlacementStrategy.
+#   Out of the box, Cassandra provides
+#   org.apache.cassandra.locator.RackUnawareStrategy and
+#   org.apache.cassandra.locator.RackAwareStrategy.  RackAwareStrategy
+#   place one replica in each of two datacenter, and other replicas in
+#   different racks in one.
+# - replication_factor: Number of replicas of each row
+# - column_families: column families associated with this keyspace
+#
+# ColumnFamily required parameters:
+# - name: name of the ColumnFamily.  Must not contain the character "-".
+# - compare_with: tells Cassandra how to sort the columns for slicing
+#   operations. The default is BytesType, which is a straightforward
+#   lexical comparison of the bytes in each column.  Other options are
+#   AsciiType, UTF8Type, LexicalUUIDType, TimeUUIDType, and LongType.
+#   You can also specify the fully-qualified class name to a class of
+#   your choice extending org.apache.cassandra.db.marshal.AbstractType.
+#
+# ColumnFamily optional parameters:
+# - keys_cached: specifies the number of keys per sstable whose
+#   locations we keep in memory in "mostly LRU" order.  (JUST the key
+#   locations, NOT any column values.) Specify a fraction (value less
+#   than 1) or an absolute number of keys to cache.  Defaults to 200000
+#   keys.
+# - rows_cached: specifies the number of rows whose entire contents we
+#   cache in memory. Do not use this on ColumnFamilies with large rows,
+#   or ColumnFamilies with high write:read ratios. Specify a fraction
+#   (value less than 1) or an absolute number of rows to cache.
+#   Defaults to 0. (i.e. row caching is off by default)
+# - comment: used to attach additional human-readable information about
+#   the column family to its definition.
+# - read_repair_chance: specifies the probability with which read
+#   repairs should be invoked on non-quorum reads.  must be between 0
+#   and 1. defaults to 1.0 (always read repair).
+# - preload_row_cache: If true, will populate row cache on startup.
+#   Defaults to false.
+#
+keyspaces:
+    - name: <%= rubber_env.app_name.capitalize %>
+      replica_placement_strategy: org.apache.cassandra.locator.RackUnawareStrategy
+      replication_factor: 1
+      column_families:
+        - name: Standard1
+          compare_with: BytesType
+
+        - name: Standard2
+          compare_with: UTF8Type
+          read_repair_chance: 0.1
+          keys_cached: 100
+
+        - name: StandardByUUID1
+          compare_with: TimeUUIDType
+
+        - name: Super1
+          column_type: Super
+          compare_with: BytesType
+          compare_subcolumns_with: BytesType
+
+        - name: Super2
+          column_type: Super
+          compare_subcolumns_with: UTF8Type
+          preload_row_cache: true
+          rows_cached: 10000
+          keys_cached: 50
+          comment: 'A column family with supercolumns, whose column and subcolumn names are UTF8 strings'
+
+        - name: Super3
+          column_type: Super
+          compare_with: LongType
+          comment: 'A column family with supercolumns, whose column names are Longs (8 bytes)'