logstash-output-redis 0.1.0

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    NDBiYmFiMWM1NDNkNzY2Mjc3ODY2ZGZjNjM5ZmFlNmE3YTEyN2NlMQ==
+  data.tar.gz: !binary |-
+    NTc0MDBkMWY4MGExN2VhODU2NDFmNzZmYWQ2ODc4NGIyNTVlMDQ2OA==
+SHA512:
+  metadata.gz: !binary |-
+    NDRmYTg3ZDJiYWFlODhhNDU2NzkyNzc1ZDE0Njk3M2ZkMjY5ODI1ZjM3MzNh
+    NjFkNDQxYzQwOTlhNWQyNWZlNTMxYzM3ZmM3NTVlYTI3ZmIyNDhkZWE0ZjQ3
+    NjYzMjI2NGJmM2YzMjQ5NzY0ZTQ1MDVjM2RlYzRjNjUzMTlkYWY=
+  data.tar.gz: !binary |-
+    NDkyODEyMjVmYjQ4NWE1MzY1YTFhZjUxZTQwZDQyODIzZTQzYjQwYjQyOWQx
+    NGVhMDczNzdmM2IzYmJiZjM3NWM0ZGU4OTQxYjZiNzE3MjkwYTRiMmUwNWE2
+    N2ZiN2NmMWQ1OTczNGQxYzFhMjAyZWMwZTA0NDBmNTYxNzI5MDU=

data/.gitignore

@@ -0,0 +1,4 @@
+*.gem
+Gemfile.lock
+.bundle
+vendor

data/Gemfile

@@ -0,0 +1,4 @@
+source 'http://rubygems.org'
+gem 'rake'
+gem 'gem_publisher'
+gem 'archive-tar-minitar'

data/Rakefile

@@ -0,0 +1,6 @@
+@files=[]
+
+task :default do
+  system("rake -T")
+end
+

data/lib/logstash/outputs/redis.rb

@@ -0,0 +1,252 @@
+# encoding: utf-8
+require "logstash/outputs/base"
+require "logstash/namespace"
+require "stud/buffer"
+
+# This output will send events to a Redis queue using RPUSH.
+# The RPUSH command is supported in Redis v0.0.7+. Using
+# PUBLISH to a channel requires at least v1.3.8+.
+# While you may be able to make these Redis versions work,
+# the best performance and stability will be found in more 
+# recent stable versions.  Versions 2.6.0+ are recommended.
+#
+# For more information about Redis, see <http://redis.io/>
+#
+class LogStash::Outputs::Redis < LogStash::Outputs::Base
+
+  include Stud::Buffer
+
+  config_name "redis"
+  milestone 2
+
+  # Name is used for logging in case there are multiple instances.
+  # TODO: delete
+  config :name, :validate => :string, :default => 'default',
+    :deprecated => true
+
+  # The hostname(s) of your Redis server(s). Ports may be specified on any
+  # hostname, which will override the global port config.
+  #
+  # For example:
+  #
+  #     "127.0.0.1"
+  #     ["127.0.0.1", "127.0.0.2"]
+  #     ["127.0.0.1:6380", "127.0.0.1"]
+  config :host, :validate => :array, :default => ["127.0.0.1"]
+
+  # Shuffle the host list during Logstash startup.
+  config :shuffle_hosts, :validate => :boolean, :default => true
+
+  # The default port to connect on. Can be overridden on any hostname.
+  config :port, :validate => :number, :default => 6379
+
+  # The Redis database number.
+  config :db, :validate => :number, :default => 0
+
+  # Redis initial connection timeout in seconds.
+  config :timeout, :validate => :number, :default => 5
+
+  # Password to authenticate with.  There is no authentication by default.
+  config :password, :validate => :password
+
+  # The name of the Redis queue (we'll use RPUSH on this). Dynamic names are
+  # valid here, for example "logstash-%{type}"
+  # TODO: delete
+  config :queue, :validate => :string, :deprecated => true
+
+  # The name of a Redis list or channel. Dynamic names are
+  # valid here, for example "logstash-%{type}".
+  # TODO set required true
+  config :key, :validate => :string, :required => false
+
+  # Either list or channel.  If `redis_type` is list, then we will set
+  # RPUSH to key. If `redis_type` is channel, then we will PUBLISH to `key`.
+  # TODO set required true
+  config :data_type, :validate => [ "list", "channel" ], :required => false
+
+  # Set to true if you want Redis to batch up values and send 1 RPUSH command
+  # instead of one command per value to push on the list.  Note that this only
+  # works with `data_type="list"` mode right now.
+  #
+  # If true, we send an RPUSH every "batch_events" events or
+  # "batch_timeout" seconds (whichever comes first).
+  # Only supported for `data_type` is "list".
+  config :batch, :validate => :boolean, :default => false
+
+  # If batch is set to true, the number of events we queue up for an RPUSH.
+  config :batch_events, :validate => :number, :default => 50
+
+  # If batch is set to true, the maximum amount of time between RPUSH commands
+  # when there are pending events to flush.
+  config :batch_timeout, :validate => :number, :default => 5
+
+  # Interval for reconnecting to failed Redis connections
+  config :reconnect_interval, :validate => :number, :default => 1
+
+  # In case Redis `data_type` is "list" and has more than @congestion_threshold items,
+  # block until someone consumes them and reduces congestion, otherwise if there are
+  # no consumers Redis will run out of memory, unless it was configured with OOM protection.
+  # But even with OOM protection, a single Redis list can block all other users of Redis,
+  # until Redis CPU consumption reaches the max allowed RAM size.
+  # A default value of 0 means that this limit is disabled.
+  # Only supported for `list` Redis `data_type`.
+  config :congestion_threshold, :validate => :number, :default => 0
+
+  # How often to check for congestion. Default is one second.
+  # Zero means to check on every event.
+  config :congestion_interval, :validate => :number, :default => 1
+
+  def register
+    require 'redis'
+
+    # TODO remove after setting key and data_type to true
+    if @queue
+      if @key or @data_type
+        raise RuntimeError.new(
+          "Cannot specify queue parameter and key or data_type"
+        )
+      end
+      @key = @queue
+      @data_type = 'list'
+    end
+
+    if not @key or not @data_type
+      raise RuntimeError.new(
+        "Must define queue, or key and data_type parameters"
+      )
+    end
+    # end TODO
+
+
+    if @batch
+      if @data_type != "list"
+        raise RuntimeError.new(
+          "batch is not supported with data_type #{@data_type}"
+        )
+      end
+      buffer_initialize(
+        :max_items => @batch_events,
+        :max_interval => @batch_timeout,
+        :logger => @logger
+      )
+    end
+
+    @redis = nil
+    if @shuffle_hosts
+        @host.shuffle!
+    end
+    @host_idx = 0
+
+    @congestion_check_times = Hash.new { |h,k| h[k] = Time.now.to_i - @congestion_interval }
+  end # def register
+
+  def receive(event)
+    return unless output?(event)
+
+    if @batch and @data_type == 'list' # Don't use batched method for pubsub.
+      # Stud::Buffer
+      buffer_receive(event.to_json, event.sprintf(@key))
+      return
+    end
+
+    key = event.sprintf(@key)
+    # TODO(sissel): We really should not drop an event, but historically
+    # we have dropped events that fail to be converted to json.
+    # TODO(sissel): Find a way to continue passing events through even
+    # if they fail to convert properly.
+    begin
+      payload = event.to_json
+    rescue Encoding::UndefinedConversionError, ArgumentError
+      puts "FAILUREENCODING"
+      @logger.error("Failed to convert event to JSON. Invalid UTF-8, maybe?",
+                    :event => event.inspect)
+      return
+    end
+
+    begin
+      @redis ||= connect
+      if @data_type == 'list'
+        congestion_check(key)
+        @redis.rpush(key, payload)
+      else
+        @redis.publish(key, payload)
+      end
+    rescue => e
+      @logger.warn("Failed to send event to Redis", :event => event,
+                   :identity => identity, :exception => e,
+                   :backtrace => e.backtrace)
+      sleep @reconnect_interval
+      @redis = nil
+      retry
+    end
+  end # def receive
+
+  def congestion_check(key)
+    return if @congestion_threshold == 0
+    if (Time.now.to_i - @congestion_check_times[key]) >= @congestion_interval # Check congestion only if enough time has passed since last check.
+      while @redis.llen(key) > @congestion_threshold # Don't push event to Redis key which has reached @congestion_threshold.
+        @logger.warn? and @logger.warn("Redis key size has hit a congestion threshold #{@congestion_threshold} suspending output for #{@congestion_interval} seconds")
+        sleep @congestion_interval
+      end
+      @congestion_check_time = Time.now.to_i
+    end
+  end
+
+  # called from Stud::Buffer#buffer_flush when there are events to flush
+  def flush(events, key, teardown=false)
+    @redis ||= connect
+    # we should not block due to congestion on teardown
+    # to support this Stud::Buffer#buffer_flush should pass here the :final boolean value.
+    congestion_check(key) unless teardown
+    @redis.rpush(key, events)
+  end
+  # called from Stud::Buffer#buffer_flush when an error occurs
+  def on_flush_error(e)
+    @logger.warn("Failed to send backlog of events to Redis",
+      :identity => identity,
+      :exception => e,
+      :backtrace => e.backtrace
+    )
+    @redis = connect
+  end
+
+  def teardown
+    if @batch
+      buffer_flush(:final => true)
+    end
+    if @data_type == 'channel' and @redis
+      @redis.quit
+      @redis = nil
+    end
+  end
+
+  private
+  def connect
+    @current_host, @current_port = @host[@host_idx].split(':')
+    @host_idx = @host_idx + 1 >= @host.length ? 0 : @host_idx + 1
+
+    if not @current_port
+      @current_port = @port
+    end
+
+    params = {
+      :host => @current_host,
+      :port => @current_port,
+      :timeout => @timeout,
+      :db => @db
+    }
+    @logger.debug(params)
+
+    if @password
+      params[:password] = @password.value
+    end
+
+    Redis.new(params)
+  end # def connect
+
+  # A string used to identify a Redis instance in log messages
+  def identity
+    @name || "redis://#{@password}@#{@current_host}:#{@current_port}/#{@db} #{@data_type}:#{@key}"
+  end
+
+end

data/logstash-output-redis.gemspec

@@ -0,0 +1,29 @@
+Gem::Specification.new do |s|
+
+  s.name            = 'logstash-output-redis'
+  s.version         = '0.1.0'
+  s.licenses        = ['Apache License (2.0)']
+  s.summary         = "This output will send events to a Redis queue using RPUSH"
+  s.description     = "This output will send events to a Redis queue using RPUSH. Requires Redis Server 2.6.0+"
+  s.authors         = ["Elasticsearch"]
+  s.email           = 'richard.pijnenburg@elasticsearch.com'
+  s.homepage        = "http://logstash.net/"
+  s.require_paths = ["lib"]
+
+  # Files
+  s.files = `git ls-files`.split($\)+::Dir.glob('vendor/*')
+
+  # Tests
+  s.test_files = s.files.grep(%r{^(test|spec|features)/})
+
+  # Special flag to let us know this is actually a logstash plugin
+  s.metadata = { "logstash_plugin" => "true", "group" => "output" }
+
+  # Gem dependencies
+  s.add_runtime_dependency 'logstash', '>= 1.4.0', '< 2.0.0'
+
+  s.add_runtime_dependency 'redis'
+  s.add_runtime_dependency 'stud'
+
+end
+

data/rakelib/publish.rake

@@ -0,0 +1,9 @@
+require "gem_publisher"
+
+desc "Publish gem to RubyGems.org"
+task :publish_gem do |t|
+  gem_file = Dir.glob(File.expand_path('../*.gemspec',File.dirname(__FILE__))).first
+  gem = GemPublisher.publish_if_updated(gem_file, :rubygems)
+  puts "Published #{gem}" if gem
+end
+

data/rakelib/vendor.rake

@@ -0,0 +1,169 @@
+require "net/http"
+require "uri"
+require "digest/sha1"
+
+def vendor(*args)
+  return File.join("vendor", *args)
+end
+
+directory "vendor/" => ["vendor"] do |task, args|
+  mkdir task.name
+end
+
+def fetch(url, sha1, output)
+
+  puts "Downloading #{url}"
+  actual_sha1 = download(url, output)
+
+  if actual_sha1 != sha1
+    fail "SHA1 does not match (expected '#{sha1}' but got '#{actual_sha1}')"
+  end
+end # def fetch
+
+def file_fetch(url, sha1)
+  filename = File.basename( URI(url).path )
+  output = "vendor/#{filename}"
+  task output => [ "vendor/" ] do
+    begin
+      actual_sha1 = file_sha1(output)
+      if actual_sha1 != sha1
+        fetch(url, sha1, output)
+      end
+    rescue Errno::ENOENT
+      fetch(url, sha1, output)
+    end
+  end.invoke
+
+  return output
+end
+
+def file_sha1(path)
+  digest = Digest::SHA1.new
+  fd = File.new(path, "r")
+  while true
+    begin
+      digest << fd.sysread(16384)
+    rescue EOFError
+      break
+    end
+  end
+  return digest.hexdigest
+ensure
+  fd.close if fd
+end
+
+def download(url, output)
+  uri = URI(url)
+  digest = Digest::SHA1.new
+  tmp = "#{output}.tmp"
+  Net::HTTP.start(uri.host, uri.port, :use_ssl => (uri.scheme == "https")) do |http|
+    request = Net::HTTP::Get.new(uri.path)
+    http.request(request) do |response|
+      fail "HTTP fetch failed for #{url}. #{response}" if [200, 301].include?(response.code)
+      size = (response["content-length"].to_i || -1).to_f
+      count = 0
+      File.open(tmp, "w") do |fd|
+        response.read_body do |chunk|
+          fd.write(chunk)
+          digest << chunk
+          if size > 0 && $stdout.tty?
+            count += chunk.bytesize
+            $stdout.write(sprintf("\r%0.2f%%", count/size * 100))
+          end
+        end
+      end
+      $stdout.write("\r      \r") if $stdout.tty?
+    end
+  end
+
+  File.rename(tmp, output)
+
+  return digest.hexdigest
+rescue SocketError => e
+  puts "Failure while downloading #{url}: #{e}"
+  raise
+ensure
+  File.unlink(tmp) if File.exist?(tmp)
+end # def download
+
+def untar(tarball, &block)
+  require "archive/tar/minitar"
+  tgz = Zlib::GzipReader.new(File.open(tarball))
+  # Pull out typesdb
+  tar = Archive::Tar::Minitar::Input.open(tgz)
+  tar.each do |entry|
+    path = block.call(entry)
+    next if path.nil?
+    parent = File.dirname(path)
+    
+    mkdir_p parent unless File.directory?(parent)
+
+    # Skip this file if the output file is the same size
+    if entry.directory?
+      mkdir path unless File.directory?(path)
+    else
+      entry_mode = entry.instance_eval { @mode } & 0777
+      if File.exists?(path)
+        stat = File.stat(path)
+        # TODO(sissel): Submit a patch to archive-tar-minitar upstream to
+        # expose headers in the entry.
+        entry_size = entry.instance_eval { @size }
+        # If file sizes are same, skip writing.
+        next if stat.size == entry_size && (stat.mode & 0777) == entry_mode
+      end
+      puts "Extracting #{entry.full_name} from #{tarball} #{entry_mode.to_s(8)}"
+      File.open(path, "w") do |fd|
+        # eof? check lets us skip empty files. Necessary because the API provided by
+        # Archive::Tar::Minitar::Reader::EntryStream only mostly acts like an
+        # IO object. Something about empty files in this EntryStream causes
+        # IO.copy_stream to throw "can't convert nil into String" on JRuby
+        # TODO(sissel): File a bug about this.
+        while !entry.eof?
+          chunk = entry.read(16384)
+          fd.write(chunk)
+        end
+          #IO.copy_stream(entry, fd)
+      end
+      File.chmod(entry_mode, path)
+    end
+  end
+  tar.close
+  File.unlink(tarball) if File.file?(tarball)
+end # def untar
+
+def ungz(file)
+
+  outpath = file.gsub('.gz', '')
+  tgz = Zlib::GzipReader.new(File.open(file))
+  begin
+    File.open(outpath, "w") do |out|
+      IO::copy_stream(tgz, out)
+    end
+    File.unlink(file)
+  rescue
+    File.unlink(outpath) if File.file?(outpath)
+   raise
+  end
+  tgz.close
+end
+
+desc "Process any vendor files required for this plugin"
+task "vendor" do |task, args|
+
+  @files.each do |file| 
+    download = file_fetch(file['url'], file['sha1'])
+    if download =~ /.tar.gz/
+      prefix = download.gsub('.tar.gz', '').gsub('vendor/', '')
+      untar(download) do |entry|
+        if !file['files'].nil?
+          next unless file['files'].include?(entry.full_name.gsub(prefix, ''))
+          out = entry.full_name.split("/").last
+        end
+        File.join('vendor', out)
+      end
+    elsif download =~ /.gz/
+      ungz(download)
+    end
+  end
+
+end

data/spec/outputs/redis_spec.rb

@@ -0,0 +1,128 @@
+require "spec_helper"
+require "logstash/outputs/redis"
+require "logstash/json"
+require "redis"
+
+describe LogStash::Outputs::Redis, :redis => true do
+  
+
+  describe "ship lots of events to a list" do
+    key = 10.times.collect { rand(10).to_s }.join("")
+    event_count = 10000 + rand(500)
+
+    config <<-CONFIG
+      input {
+        generator {
+          message => "hello world"
+          count => #{event_count}
+          type => "generator"
+        }
+      }
+      output {
+        redis {
+          host => "127.0.0.1"
+          key => "#{key}"
+          data_type => list
+        }
+      }
+    CONFIG
+
+    agent do
+      # Query redis directly and inspect the goodness.
+      redis = Redis.new(:host => "127.0.0.1")
+
+      # The list should contain the number of elements our agent pushed up.
+      insist { redis.llen(key) } == event_count
+
+      # Now check all events for order and correctness.
+      event_count.times do |value|
+        id, element = redis.blpop(key, 0)
+        event = LogStash::Event.new(LogStash::Json.load(element))
+        insist { event["sequence"] } == value
+        insist { event["message"] } == "hello world"
+      end
+
+      # The list should now be empty
+      insist { redis.llen(key) } == 0
+    end # agent
+  end
+
+  describe "batch mode" do
+    key = 10.times.collect { rand(10).to_s }.join("")
+    event_count = 200000
+
+    config <<-CONFIG
+      input {
+        generator {
+          message => "hello world"
+          count => #{event_count}
+          type => "generator"
+        }
+      }
+      output {
+        redis {
+          host => "127.0.0.1"
+          key => "#{key}"
+          data_type => list
+          batch => true
+          batch_timeout => 5
+          timeout => 5
+        }
+      }
+    CONFIG
+
+    agent do
+      # we have to wait for teardown to execute & flush the last batch.
+      # otherwise we might start doing assertions before everything has been
+      # sent out to redis.
+      sleep 2
+
+      redis = Redis.new(:host => "127.0.0.1")
+
+      # The list should contain the number of elements our agent pushed up.
+      insist { redis.llen(key) } == event_count
+
+      # Now check all events for order and correctness.
+      event_count.times do |value|
+        id, element = redis.blpop(key, 0)
+        event = LogStash::Event.new(LogStash::Json.load(element))
+        insist { event["sequence"] } == value
+        insist { event["message"] } == "hello world"
+      end
+
+      # The list should now be empty
+      insist { redis.llen(key) } == 0
+    end # agent
+  end
+
+  describe "converts US-ASCII to utf-8 without failures" do
+    key = 10.times.collect { rand(10).to_s }.join("")
+
+    config <<-CONFIG
+      input {
+        generator {
+          charset => "US-ASCII"
+          message => "\xAD\u0000"
+          count => 1
+          type => "generator"
+        }
+      }
+      output {
+        redis {
+          host => "127.0.0.1"
+          key => "#{key}"
+          data_type => list
+        }
+      }
+    CONFIG
+
+    agent do
+      # Query redis directly and inspect the goodness.
+      redis = Redis.new(:host => "127.0.0.1")
+
+      # The list should contain no elements.
+      insist { redis.llen(key) } == 1
+    end # agent
+  end
+end
+

metadata

@@ -0,0 +1,103 @@
+--- !ruby/object:Gem::Specification
+name: logstash-output-redis
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Elasticsearch
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-11-03 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: logstash
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.4.0
+    - - <
+      - !ruby/object:Gem::Version
+        version: 2.0.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.4.0
+    - - <
+      - !ruby/object:Gem::Version
+        version: 2.0.0
+- !ruby/object:Gem::Dependency
+  name: redis
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: stud
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: This output will send events to a Redis queue using RPUSH. Requires Redis
+  Server 2.6.0+
+email: richard.pijnenburg@elasticsearch.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Rakefile
+- lib/logstash/outputs/redis.rb
+- logstash-output-redis.gemspec
+- rakelib/publish.rake
+- rakelib/vendor.rake
+- spec/outputs/redis_spec.rb
+homepage: http://logstash.net/
+licenses:
+- Apache License (2.0)
+metadata:
+  logstash_plugin: 'true'
+  group: output
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.1
+signing_key: 
+specification_version: 4
+summary: This output will send events to a Redis queue using RPUSH
+test_files:
+- spec/outputs/redis_spec.rb