hadoop-metrics 0.1.0

data/Gemfile

@@ -0,0 +1,3 @@
+source "https://rubygems.org"
+
+gemspec

data/LICENSE.txt

@@ -0,0 +1,7 @@
+Copyright (C) 2013 Masahiro Nakagawa
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,60 @@
+# hadoop-metrics
+
+hadoop-metrics is a wrapper for Hadoop Metrics API.
+
+## Installation
+
+### gem
+
+```
+gem install hadoop-metrics
+```
+
+## Usage
+
+### Setup
+
+Without `jmx` method, getting metrics depends on /metrics API.
+So if you use this library, then you should enable dumping each metrics via hadoop-metrics.properties.
+
+```
+# example
+mapred.class=org.apache.hadoop.metrics.spi.NoEmitMetricsContext
+mapred.period=30 
+```
+
+### JobTracker
+
+```
+require 'hadoop_metrics/job_tracker'
+
+jt = HadoopMetrics::JobTracker.new('localhost', 50030)
+puts JSON.pretty_generate(jt.fairscheduler_jobs)
+```
+
+### TaskTracker
+
+```
+require 'hadoop_metrics/job_tracker'
+
+tt = HadoopMetrics::TaskTracker.new('localhost', 50060)
+puts JSON.pretty_generate(tt.shuffle_output)
+```
+
+### NOTE
+
+NameNode and DataNode are not supported yet.
+
+## Copyright
+
+<table>
+  <tr>
+    <td>Author</td><td>Masahiro Nakagawa <repeatedly@gmail.com></td>
+  </tr>
+  <tr>
+    <td>Copyright</td><td>Copyright (c) 2013- Masahiro Nakagawa</td>
+  </tr>
+  <tr>
+    <td>License</td><td>MIT License</td>
+  </tr>
+</table>

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/hadoop-metrics.gemspec

@@ -0,0 +1,19 @@
+$:.push File.expand_path("../lib", __FILE__)
+require "hadoop_metrics/version"
+
+Gem::Specification.new do |s|
+  s.name        = "hadoop-metrics"
+  s.version     = HadoopMetrics::VERSION
+  s.authors     = ["Masahiro Nakagawa"]
+  s.email       = ["repeatedly@gmail.com"]
+  s.homepage    = "https://github.com/repeatedly/hadoop-metrics"
+  s.summary     = %q{Wrapper for Hadoop Metrics API}
+  s.description = s.summary
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+
+  s.add_development_dependency "rake", ">= 0.9.2"
+end

data/lib/hadoop_metrics.rb

@@ -0,0 +1,13 @@
+require 'hadoop_metrics/job_tracker'
+require 'hadoop_metrics/task_tracker'
+
+jt = HadoopMetrics::JobTracker.new('localhost', 50030, :snake_case => false)
+#puts JSON.pretty_generate(jt.fairscheduler_jobs)
+#puts JSON.pretty_generate(jt.mapred_jobtracker('hostName'))
+#puts JSON.pretty_generate(jt.fairscheduler_pools)
+puts JSON.pretty_generate(jt.fairscheduler_running_tasks)
+#puts JSON.pretty_generate(jt.jmx)
+
+#tt = HadoopMetrics::TaskTracker.new('localhost', 50060, :snake_case => false)
+#puts JSON.pretty_generate(tt.shuffle_output)
+#puts JSON.pretty_generate(tt.mapred)

data/lib/hadoop_metrics/api.rb

@@ -0,0 +1,71 @@
+require 'net/http'
+require 'json'
+
+module HadoopMetrics
+  module API
+    def jmx
+      jmx_json = HadoopMetrics.get_response(@jmx_endpoint)['beans'].first
+      @json_value_fields.each { |f|
+        jmx_json[f] = JSON.parse(jmx_json[f])
+      }
+      if @snake_case
+        jmx_json = HadoopMetrics.snake_cased(jmx_json)
+      end
+
+      jmx_json
+    end
+
+    def metrics
+      HadoopMetrics.get_response(@metrics_endpoint)
+    end
+
+    private
+
+    def group_by(category, target, column)
+      categories = metrics[category]
+      return nil if categories.nil?
+
+      targets = categories[target]
+      return nil if targets.nil?
+
+      targets.map { |target|
+        HadoopMetrics.merge_data(target, @snake_case)
+      }.group_by { |target|
+        target[column]
+      }
+    end
+
+    def method_missing(method, *args)
+      category, target = method.to_s.split('_', 2)
+      group_by(category, target, *args)
+    end
+  end
+
+  def self.get_response(endpoint)
+    response = Net::HTTP.get_response(endpoint)
+    if response.code.to_i == 200
+      JSON.parse(response.body)
+    else
+      raise "Failed to get a response: code = #{response.code}, body = #{response.body}"
+    end
+  end
+
+  def self.merge_data(data, snake_case)
+    f = data.first
+    f.merge!(data.last)
+    snake_case ? snake_cased(f) : f
+  end
+
+  def self.to_snake_case(name)
+    name[0] = name[0].chr.downcase
+    name.gsub(/[A-Z]/) { |n| "_#{n.downcase}" }
+  end
+
+  def self.snake_cased(json)
+    snake_cased = {}
+    json.each_pair { |k, v|
+      snake_cased[HadoopMetrics.to_snake_case(k.dup)] = json[k]
+    }
+    snake_cased
+  end
+end

data/lib/hadoop_metrics/job_tracker.rb

@@ -0,0 +1,38 @@
+require 'hadoop_metrics/api'
+
+module HadoopMetrics
+  class JobTracker
+    include API
+
+    def initialize(host, port, opts = {})
+      @jmx_endpoint = URI("http://#{host}:#{port}/jmx?qry=hadoop:service=JobTracker,name=JobTrackerInfo")
+      @metrics_endpoint = URI("http://#{host}:#{port}/metrics?format=json")
+      @json_value_fields = %W(SummaryJson AliveNodesInfoJson BlacklistedNodesInfoJson QueueInfoJson)
+      @snake_case = opts.has_key?(:snake_case) ? opts[:snake_case] : true
+    end
+
+    def fairscheduler_pools(column = 'name')
+      group_by('fairscheduler', 'pools', column)
+    end
+
+    def fairscheduler_jobs(column = 'name')
+      group_by('fairscheduler','jobs', column)
+    end
+
+    def fairscheduler_running_tasks(target = 'pools')
+      fs = metrics['fairscheduler']
+      return nil if fs.nil?
+
+      targets = fs[target]
+      return nil if targets.nil?
+
+      each_tasks = {}
+      targets.each { |target|
+        name = target.first['name']
+        each_tasks[name] ||= 0
+        each_tasks[name] += target.last['runningTasks']
+      }
+      each_tasks
+    end
+  end
+end

data/lib/hadoop_metrics/task_tracker.rb

@@ -0,0 +1,24 @@
+require 'hadoop_metrics/api'
+
+module HadoopMetrics
+  class TaskTracker
+    include API
+
+    def initialize(host, port, opts = {})
+      @jmx_endpoint = URI("http://#{host}:#{port}/jmx?qry=hadoop:service=TaskTracker,name=TaskTrackerInfo")
+      @metrics_endpoint = URI("http://#{host}:#{port}/metrics?format=json")
+      @json_value_fields = %W(TasksInfoJson)
+      @snake_case = opts[:snake_case] || true
+    end
+
+    def shuffle_output(column = 'sessionId')
+      column = HadoopMetrics.to_snake_case(column) if @snake_case
+      group_by('mapred', 'shuffleOutput', column)
+    end
+
+    def mapred(column = 'sessionId')
+      column = HadoopMetrics.to_snake_case(column) if @snake_case
+      group_by('mapred', 'tasktracker', column)
+    end
+  end
+end

data/lib/hadoop_metrics/version.rb

@@ -0,0 +1,3 @@
+module HadoopMetrics
+  VERSION = '0.1.0'
+end

metadata

@@ -0,0 +1,77 @@
+--- !ruby/object:Gem::Specification
+name: hadoop-metrics
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+  prerelease: 
+platform: ruby
+authors:
+- Masahiro Nakagawa
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-04-25 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 0.9.2
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 0.9.2
+description: Wrapper for Hadoop Metrics API
+email:
+- repeatedly@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- hadoop-metrics.gemspec
+- lib/hadoop_metrics.rb
+- lib/hadoop_metrics/api.rb
+- lib/hadoop_metrics/job_tracker.rb
+- lib/hadoop_metrics/task_tracker.rb
+- lib/hadoop_metrics/version.rb
+homepage: https://github.com/repeatedly/hadoop-metrics
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+      segments:
+      - 0
+      hash: 2512778794185577650
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+      segments:
+      - 0
+      hash: 2512778794185577650
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.23
+signing_key: 
+specification_version: 3
+summary: Wrapper for Hadoop Metrics API
+test_files: []