workflow_manager 0.2.5 → 0.2.6

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--require spec_helper

data/bin/wfm_monitoring

@@ -1,7 +1,7 @@
 #!/usr/bin/env ruby
 # encoding: utf-8
 # 20121112 masa workflow manager client
-Version = '20131104-192323'
+Version = '20160317-153614'
 
 require 'drb/drb' 
 require 'workflow_manager/optparse_ex'
@@ -52,4 +52,5 @@ sge_options << "-n #{opt.nodes}" if opt.nodes
 
 script_content = File.read(script_file)
 workflow_manager = DRbObject.new_with_uri(uri)
-puts workflow_manager.start_monitoring(script_file, user, 0, script_content, project_number, sge_options.join(' '), opt.log)
+#puts workflow_manager.start_monitoring(script_file, user, 0, script_content, project_number, sge_options.join(' '), opt.log)
+puts workflow_manager.start_monitoring2(script_file, script_content, user, project_number, sge_options.join(' '), opt.log)

data/lib/workflow_manager/cluster.rb

@@ -26,6 +26,8 @@ module WorkflowManager
     end
     def job_ends?(log_file)
     end
+    def job_pending?(job_id)
+    end
     def copy_commands(org_dir, dest_parent_dir, now=nil)
     end
     def kill_command(job_id)
@@ -105,7 +107,8 @@ module WorkflowManager
      qstat_flag = false
       IO.popen('qstat -u "*"') do |io|
         while line=io.gets
-          if line =~ /#{job_id}/
+          jobid, prior, name, user, state, *others = line.chomp.split
+          if jobid.strip == job_id and state == 'r'
             qstat_flag = true
             break
           end
@@ -125,6 +128,19 @@ module WorkflowManager
       end
       log_flag
     end
+    def job_pending?(job_id)
+     qstat_flag = false
+      IO.popen('qstat -u "*"') do |io|
+        while line=io.gets
+          jobid, prior, name, user, state, *others = line.chomp.split
+          if jobid.strip == job_id and state == 'qw'
+            qstat_flag = true
+            break
+          end
+        end
+      end
+      qstat_flag
+    end
     def copy_commands(org_dir, dest_parent_dir, now=nil)
       commands = if now
                    ["g-req copynow #{org_dir} #{dest_parent_dir}"]

data/lib/workflow_manager/server.rb

@@ -3,6 +3,7 @@
 
 require 'drb/drb' 
 require 'fileutils'
+require 'csv'
 begin
   require 'kyotocabinet'
   NO_KYOTO = false
@@ -105,7 +106,7 @@ module WorkflowManager
       log_puts("Server starts")
     end
     def hello
-      'hello, '+ @cluster.name
+      'hello test hoge, '+ @cluster.name
     end
     def copy_commands(org_dir, dest_parent_dir, now=nil)
       @cluster.copy_commands(org_dir, dest_parent_dir, now)
@@ -131,6 +132,111 @@ module WorkflowManager
          end
       end
     end
+    def input_dataset_tsv_path(script_content)
+      gstore_dir = nil
+      path = nil
+      script_content.split(/\n/).each do |line|
+        if line =~ /GSTORE_DIR=(.+)/
+          gstore_dir = $1.chomp
+        elsif line =~ /INPUT_DATASET=(.+)/
+          path = $1.chomp
+          break
+        end
+      end
+      [gstore_dir, path]
+    end
+    def input_dataset_file_list(dataset_tsv_path)
+      file_list = []
+      CSV.foreach(dataset_tsv_path, :headers=>true, :col_sep=>"\t") do |row|
+        row.each do |header, value|
+          if header =~ /\[File\]/
+            file_list << value
+          end
+        end
+      end
+      file_list
+    end
+    def input_dataset_exist?(file_list)
+      flag = true
+      file_list.each do |file|
+        unless File.exist?(file)
+          flag = false
+          break
+        end
+      end
+      flag
+    end
+    def update_time_status(job_id, current_status, script_name, user, project_number)
+      # if the current status changed from last time, then save, otherwise do nothing
+      # once status changes into success or fail, then the thread is expected to be killed in later process
+      @statuses.transaction do |statuses|
+        start_time = nil
+        if stat = statuses[job_id] 
+          last_status, script_name, start_time, user, project_number = stat.split(/,/)
+        end
+        time = if start_time 
+                 if current_status == 'success' or current_status == 'fail'
+                   start_time + '/' + Time.now.strftime("%Y-%m-%d %H:%M:%S")
+                 elsif current_status != last_status
+                   Time.now.strftime("%Y-%m-%d %H:%M:%S")
+                 end
+               else
+                 Time.now.strftime("%Y-%m-%d %H:%M:%S")
+               end
+        if time
+          statuses[job_id] = [current_status, script_name, time, user, project_number].join(',')
+        end
+      end
+    end
+    def finalize_monitoring(current_status, log_file, log_dir)
+      if current_status == 'success' or current_status == 'fail'
+        unless log_dir.empty?
+          copy_commands(log_file, log_dir).each do |command|
+            log_puts(command)
+            system command
+          end
+          err_file = log_file.gsub('_o.log','_e.log')
+          copy_commands(err_file, log_dir).each do |command|
+            log_puts(command)
+            system command
+          end
+        end
+        Thread.current.kill
+      end
+    end
+    def start_monitoring2(script_path, script_content, user='sushi_lover', project_number=0, sge_options='', log_dir='')
+      # script_path is only used to generate a log file name
+      # It is not used to read the script contents
+      gstore_dir, input_dataset = input_dataset_tsv_path(script_content)
+      if gstore_dir and input_dataset
+        path = File.join(gstore_dir, input_dataset)
+        file_list = input_dataset_file_list(path)
+        if input_dataset_exist?(file_list)
+          # wait until the files come
+        end
+      end
+
+      job_id, log_file, command = @cluster.submit_job(script_path, script_content, sge_options)
+
+      if job_id and log_file
+        worker = Thread.new(job_id, log_file, log_dir, script_path) do |job_id, log_file, log_dir, script_path|
+          loop do
+            # check status
+            current_status = check_status(job_id, log_file)
+
+            # save time and status
+            update_time_status(job_id, current_status, script_path, user, project_number)
+
+            # finalize (kill current thred) in case of success or fail 
+            finalize_monitoring(current_status, log_file, log_dir)
+
+            # wait
+            sleep @interval
+          end # loop
+        end # thread
+        job_id
+      end
+    end
     def start_monitoring(submit_command, user = 'sushi lover', resubmit = 0, script = '', project_number = 0, sge_options='', log_dir = '')
       log_puts("monitoring: script=" + submit_command + " user=" + user + " resubmit=" + resubmit.to_s + " project=" + project_number.to_s + " sge option=" + sge_options + " log dir=" + log_dir.to_s)
 
@@ -227,7 +333,7 @@ module WorkflowManager
       #@statuses.open(@db_stat)
       @statuses.transaction do |statuses|
         if new_status and stat = statuses[job_id.to_s]
-          status_list = ['success', 'running', 'fail']
+          status_list = ['success', 'running', 'pending', 'fail']
           if status_list.include?(new_status)
             items = stat.split(/,/)
             items.shift
@@ -294,17 +400,17 @@ module WorkflowManager
       script
     end
     def success_or_fail(job_id, log_file)
-      job_running = @cluster.job_running?(job_id)
-      job_ends = @cluster.job_ends?(log_file)
-      msg = if job_running
+      msg = if @cluster.job_running?(job_id)
               'running'
-            elsif job_ends
+            elsif @cluster.job_ends?(log_file)
               'success'
+            elsif @cluster.job_pending?(job_id)
+              'pending'
             else
               'fail'
             end
-      msg
     end
+    alias_method :check_status, :success_or_fail
   end
 end
 

data/lib/workflow_manager/version.rb

@@ -1,3 +1,3 @@
 module WorkflowManager
-  VERSION = "0.2.5"
+  VERSION = "0.2.6"
 end

data/spec/cluster_spec.rb

@@ -0,0 +1,97 @@
+#!/usr/bin/env ruby
+# encoding: utf-8
+
+require './lib/workflow_manager/cluster'
+
+include WorkflowManager
+describe Cluster do
+  subject(:cluster) {Cluster.new}
+  context 'when new' do
+    it {is_expected.to be_an_instance_of Cluster} # RSpec3
+#    it {should be_an_instance_of Cluster} # RSpec2
+#    example {expect(cluster).to be_an_instance_of Cluster} # RSpec3
+#    its(:options) {should be_empty} # RSpec2, does not work anymore
+#    example {expect(cluster.options).to be_empty}
+  end 
+  describe '#job_running?' do
+    subject {cluster.job_running?('job_id')}
+    it {is_expected.to be_nil}
+  end
+  describe '#job_ends?' do
+    subject {cluster.job_ends?('log_file')}
+    it {is_expected.to be_nil}
+  end
+  describe '#job_pending?' do
+    subject {cluster.job_pending?('job_id')}
+    it {is_expected.to be_nil}
+  end
+end
+
+describe FGCZCluster do
+  subject(:cluster) {FGCZCluster.new}
+  context 'when new' do
+    it {is_expected.to be_an_instance_of FGCZCluster}
+  end
+  describe '#job_running?' do
+    let(:line) {'  72757 0.50661 Gcal017211 pacbio       r     03/11/2016'}
+    let(:job_id) {'72757'}
+    subject {cluster.job_running?(job_id)}
+    let(:io) {double('io')}
+    before do
+      allow(IO).to receive(:popen).and_yield(io)
+    end
+    context 'when running' do
+      before do
+        allow(io).to receive(:gets).and_return(line)
+      end
+      it {is_expected.to eq true}
+    end
+    context 'when not running?' do
+      before do
+        allow(io).to receive(:gets).and_return(nil)
+      end
+      it {is_expected.to eq false}
+    end
+  end
+  describe '#job_ends?' do
+    let(:log_file) {'log_file'}
+    subject {cluster.job_ends?(log_file)}
+    let(:io) {double('io')}
+    before do
+      allow(IO).to receive(:popen).and_yield(io)
+    end
+    context 'when job ends' do
+      before do
+        allow(io).to receive(:gets).and_return('__SCRIPT END__')
+      end
+      it {is_expected.to eq true}
+    end
+    context 'when job not ends' do
+      before do
+        allow(io).to receive(:gets).and_return(nil)
+      end
+      it {is_expected.to eq false}
+    end
+  end
+  describe '#job_pending?' do
+    let(:job_id) {'1234'}
+    let(:line) {'  1234 0.50661 Gcal017211 pacbio       qw     03/11/2016'}
+    subject {cluster.job_pending?(job_id)}
+    let(:io) {double('io')}
+    before do
+      allow(IO).to receive(:popen).and_yield(io)
+    end
+    context 'when pending' do
+      before do
+        allow(io).to receive(:gets).and_return(line)
+      end
+      it {is_expected.to eq true}
+    end
+    context 'when not pending' do
+      before do
+        allow(io).to receive(:gets).and_return(nil)
+      end
+      it {is_expected.to eq false}
+    end
+  end
+end

data/spec/server_spec.rb

@@ -0,0 +1,210 @@
+#!/usr/bin/env ruby
+# encoding: utf-8
+
+require './lib/workflow_manager/server'
+
+include WorkflowManager
+describe Server do
+  subject(:server) {Server.new}
+  let(:cluster){double('local_computer')}
+  before do
+    WorkflowManager::Server.configure do |config|
+      config.log_dir = '/srv/GT/analysis/masaomi/workflow_manager/run_workflow_manager/logs'
+      config.db_dir = '/srv/GT/analysis/masaomi/workflow_manager/run_workflow_manager/dbs'
+      config.interval = 30
+      config.resubmit = 0
+      #config.cluster = WorkflowManager::LocalComputer.new('local_computer')
+      config.cluster = cluster
+      allow(config.cluster).to receive_messages(:log_dir= => nil, :name => 'local_computer')
+    end
+    # suppress puts
+    allow($stdout).to receive(:write)
+  end
+  context 'when new' do
+    it {is_expected.to be_an_instance_of Server} # RSpec3
+  end 
+  describe '#input_dataset_exist?' do
+    let(:file_list) {['file1', 'file2']}
+    subject{server.input_dataset_exist?(file_list)}
+    context 'when file exist' do 
+      before do
+        allow(File).to receive(:exist?).and_return(true)
+      end
+      it {is_expected.to eq true}
+    end
+    context 'when file not exist' do
+      before do
+        allow(File).to receive(:exist?).and_return(false)
+      end
+      it {is_expected.to eq false}
+    end
+  end
+  describe '#input_dataset_file_list' do
+      subject{server.input_dataset_file_list('input_dataset_tsv_path')}
+      let(:rows) {{'Read1 [File]'=>'file1', 'Read2 [File]'=>'file2'} }
+      before do
+        allow(CSV).to receive(:foreach).and_yield(rows)
+      end
+      let(:sample_file_list) { ['file1', 'file2'] }
+      it {is_expected.to eq sample_file_list}
+  end
+  describe '#input_dataset_tsv_path' do
+    let(:sample_script) {
+      "SCRATCH_DIR=/scratch/test_masa_2016-03-03--16-36-42_temp$$
+GSTORE_DIR=/srv/gstore/projects
+INPUT_DATASET=/srv/gstore/projects/p1535/test_masa/input_dataset.tsv"
+    }
+    let(:path){
+      [
+        '/srv/gstore/projects',
+        '/srv/gstore/projects/p1535/test_masa/input_dataset.tsv'
+      ]
+    }
+    subject{server.input_dataset_tsv_path(sample_script)}
+    it {is_expected.to eq path}
+  end
+  describe '#start_monitoring2' do
+    let(:script_path){'script_file'}
+    let(:script_content){'script_content'}
+    let(:cluster){double('cluster')}
+    before do
+      allow(server).to receive(:input_dataset_tsv_path)
+      allow(server).to receive(:input_dataset_file_list)
+      allow(server).to receive(:input_dataset_exist?)
+    end
+    context 'when submit_job failed' do
+      before do
+        allow(cluster).to receive(:submit_job)
+      end
+      subject {server.start_monitoring2(script_path, script_content)}
+      it {is_expected.to be_nil}
+    end
+    context 'when submit_job successed' do
+      before do
+        allow(cluster).to receive(:submit_job).and_return(['job_id', 'log_file', 'command'])
+        allow(Thread).to receive(:new)
+      end
+      subject {server.start_monitoring2(script_path, script_content)}
+      it {is_expected.to eq 'job_id'}
+    end
+  end
+  describe '#success_or_fail' do
+    let(:job_id){'job_id'}
+    let(:log_file){'log_file'}
+    let(:cluster){double('cluster')}
+    before do
+      server.instance_variable_set(:@cluster, cluster)
+    end
+    context 'when job running' do
+      before do
+        allow(cluster).to receive(:job_running?).and_return(true)
+        allow(cluster).to receive(:job_ends?).and_return(nil)
+        allow(cluster).to receive(:job_pending?).and_return(nil)
+      end
+      subject {server.success_or_fail(job_id, log_file)}
+      it {is_expected.to eq 'running'}
+    end
+    context 'when job ends' do
+      before do
+        allow(cluster).to receive(:job_running?).and_return(nil)
+        allow(cluster).to receive(:job_ends?).and_return(true)
+        allow(cluster).to receive(:job_pending?).and_return(nil)
+      end
+      subject {server.success_or_fail(job_id, log_file)}
+      it {is_expected.to eq 'success'}
+    end
+    context 'when job pending' do
+      before do
+        allow(cluster).to receive(:job_running?).and_return(nil)
+        allow(cluster).to receive(:job_ends?).and_return(nil)
+        allow(cluster).to receive(:job_pending?).and_return(true)
+      end
+      subject {server.success_or_fail(job_id, log_file)}
+      it {is_expected.to eq 'pending'}
+    end
+  end
+  describe '#status' do
+    let(:statuses) {double('statuses')}
+    before do 
+      server.instance_variable_set(:@statuses, statuses)
+    end
+    context 'when read status' do 
+      before do
+        allow(statuses).to receive(:transaction).and_yield({'job_id'=>'stat'})
+      end
+      subject {server.status('job_id')}
+      it {is_expected.to eq 'stat'}
+    end
+    context 'when assign status' do
+      before do
+        allow(statuses).to receive(:transaction).and_yield({'job_id'=>'running'})
+      end
+      subject {server.status('job_id', 'success')}
+      it {is_expected.to eq 'success'}
+    end
+  end
+  describe '#update_time_status' do
+    let(:statuses) {double('statuses')}
+    before do 
+      server.instance_variable_set(:@statuses, statuses)
+    end
+    context 'when initial call' do
+      before do
+        allow(statuses).to receive(:transaction).and_yield({'job_id' => nil})
+        allow(Time).to receive_message_chain(:now, :strftime).and_return('time')
+      end
+      let(:expected) {'current_status,script_name,time,user,project_number'}
+      subject {server.update_time_status('job_id', 'current_status', 'script_name', 'user', 'project_number')}
+      it {is_expected.to eq expected}
+    end
+    context 'when changing status from running to success' do
+      let(:last_status) {'running,script_name,start_time,user,project_number'}
+      before do
+        allow(statuses).to receive(:transaction).and_yield({'job_id' => last_status})
+        allow(Time).to receive_message_chain(:now, :strftime).and_return('end_time')
+      end
+      subject {server.update_time_status('job_id', 'success', 'script_name', 'user', 'project_number')}
+      let(:expected) {'success,script_name,start_time/end_time,user,project_number'}
+      it {is_expected.to eq expected}
+    end
+    context 'when current_status and new_sutatus are same' do
+      let(:last_status) {'running,script_name,start_time,user,project_number'}
+      before do
+        allow(statuses).to receive(:transaction).and_yield({'job_id' => last_status})
+        allow(Time).to receive_message_chain(:now, :strftime).and_return('end_time')
+      end
+      subject {server.update_time_status('job_id', 'running', 'script_name', 'user', 'project_number')}
+      it {is_expected.to be_nil}
+    end
+    context 'when current_status==running and last_status==pending' do
+      let(:last_status) {'pending,script_name,start_time,user,project_number'}
+      before do
+        allow(statuses).to receive(:transaction).and_yield({'job_id' => last_status})
+        allow(Time).to receive_message_chain(:now, :strftime).and_return('end_time')
+      end
+      subject {server.update_time_status('job_id', 'running', 'script_name', 'user', 'project_number')}
+      let(:expected) {"running,script_name,end_time,user,project_number"}
+      it {is_expected.to eq expected}
+    end
+  end
+  describe '#finalize_monitoring' do
+    context 'when status == running' do
+      before do
+        allow(server).to receive(:log_puts)
+        allow(Thread).to receive_message_chain(:current, :kill)
+      end
+      subject {server.finalize_monitoring('running', 'log_file', 'log_dir')}
+      it {is_expected.to be_nil}
+    end
+    context 'when status == success' do
+      before do
+        allow(server).to receive(:log_puts)
+        allow(Thread).to receive_message_chain(:current, :kill)
+        #expect(server).to receive(:system).twice
+        expect(server).to receive(:copy_commands).twice.and_return([])
+      end
+      subject {server.finalize_monitoring('success', 'log_file', 'log_dir')}
+      it {is_expected.to be_nil}
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,96 @@
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# The generated `.rspec` file contains `--require spec_helper` which will cause
+# this file to always be loaded, without a need to explicitly require it in any
+# files.
+#
+# Given that it is always loaded, you are encouraged to keep this file as
+# light-weight as possible. Requiring heavyweight dependencies from this file
+# will add to the boot time of your test suite on EVERY test run, even for an
+# individual file that may not need all of that loaded. Instead, consider making
+# a separate helper file that requires the additional dependencies and performs
+# the additional setup, and require it from the spec files that actually need
+# it.
+#
+# The `.rspec` file also contains a few flags that are not defaults but that
+# users commonly want.
+#
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+RSpec.configure do |config|
+  # rspec-expectations config goes here. You can use an alternate
+  # assertion/expectation library such as wrong or the stdlib/minitest
+  # assertions if you prefer.
+  config.expect_with :rspec do |expectations|
+    # This option will default to `true` in RSpec 4. It makes the `description`
+    # and `failure_message` of custom matchers include text for helper methods
+    # defined using `chain`, e.g.:
+    #     be_bigger_than(2).and_smaller_than(4).description
+    #     # => "be bigger than 2 and smaller than 4"
+    # ...rather than:
+    #     # => "be bigger than 2"
+    expectations.include_chain_clauses_in_custom_matcher_descriptions = true
+  end
+
+  # rspec-mocks config goes here. You can use an alternate test double
+  # library (such as bogus or mocha) by changing the `mock_with` option here.
+  config.mock_with :rspec do |mocks|
+    # Prevents you from mocking or stubbing a method that does not exist on
+    # a real object. This is generally recommended, and will default to
+    # `true` in RSpec 4.
+    mocks.verify_partial_doubles = true
+  end
+
+# The settings below are suggested to provide a good initial experience
+# with RSpec, but feel free to customize to your heart's content.
+=begin
+  # These two settings work together to allow you to limit a spec run
+  # to individual examples or groups you care about by tagging them with
+  # `:focus` metadata. When nothing is tagged with `:focus`, all examples
+  # get run.
+  config.filter_run :focus
+  config.run_all_when_everything_filtered = true
+
+  # Allows RSpec to persist some state between runs in order to support
+  # the `--only-failures` and `--next-failure` CLI options. We recommend
+  # you configure your source control system to ignore this file.
+  config.example_status_persistence_file_path = "spec/examples.txt"
+
+  # Limits the available syntax to the non-monkey patched syntax that is
+  # recommended. For more details, see:
+  #   - http://rspec.info/blog/2012/06/rspecs-new-expectation-syntax/
+  #   - http://www.teaisaweso.me/blog/2013/05/27/rspecs-new-message-expectation-syntax/
+  #   - http://rspec.info/blog/2014/05/notable-changes-in-rspec-3/#zero-monkey-patching-mode
+  config.disable_monkey_patching!
+
+  # This setting enables warnings. It's recommended, but in some cases may
+  # be too noisy due to issues in dependencies.
+  config.warnings = true
+
+  # Many RSpec users commonly either run the entire suite or an individual
+  # file, and it's useful to allow more verbose output when running an
+  # individual spec file.
+  if config.files_to_run.one?
+    # Use the documentation formatter for detailed output,
+    # unless a formatter has already been configured
+    # (e.g. via a command-line flag).
+    config.default_formatter = 'doc'
+  end
+
+  # Print the 10 slowest examples and example groups at the
+  # end of the spec run, to help surface which specs are running
+  # particularly slow.
+  config.profile_examples = 10
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = :random
+
+  # Seed global randomization in this process using the `--seed` CLI option.
+  # Setting this allows you to use `--seed` to deterministically reproduce
+  # test failures related to randomization by passing the same `--seed` value
+  # as the one that triggered the failure.
+  Kernel.srand config.seed
+=end
+end

metadata

@@ -2,7 +2,7 @@
 name: workflow_manager
 version: !ruby/object:Gem::Version 
   prerelease: 
-  version: 0.2.5
+  version: 0.2.6
 platform: ruby
 authors: 
 - Functional Genomics Center Zurich
@@ -10,7 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2015-10-15 00:00:00 Z
+date: 2016-03-21 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: bundler
@@ -53,6 +53,7 @@ extra_rdoc_files: []
 
 files: 
 - .gitignore
+- .rspec
 - Gemfile
 - LICENSE.txt
 - README.md
@@ -73,6 +74,9 @@ files:
 - lib/workflow_manager/optparse_ex.rb
 - lib/workflow_manager/server.rb
 - lib/workflow_manager/version.rb
+- spec/cluster_spec.rb
+- spec/server_spec.rb
+- spec/spec_helper.rb
 - workflow_manager.gemspec
 homepage: ""
 licenses: 
@@ -101,5 +105,7 @@ rubygems_version: 1.8.23
 signing_key: 
 specification_version: 3
 summary: Workflow Manager manages job submissions using dRuby.
-test_files: []
-
+test_files: 
+- spec/cluster_spec.rb
+- spec/server_spec.rb
+- spec/spec_helper.rb