efficiency20-delayed_job 1.8.51

data/lib/delayed/job.rb

@@ -0,0 +1,296 @@
+require 'timeout'
+
+module Delayed
+
+  class DeserializationError < StandardError
+  end
+
+  # A job object that is persisted to the database.
+  # Contains the work object as a YAML field.
+  class Job < ActiveRecord::Base
+    @@max_attempts = 25
+    @@max_run_time = 4.hours
+
+    cattr_accessor :max_attempts, :max_run_time
+
+    set_table_name :delayed_jobs
+
+    # By default failed jobs are destroyed after too many attempts.
+    # If you want to keep them around (perhaps to inspect the reason
+    # for the failure), set this to false.
+    cattr_accessor :destroy_failed_jobs
+    self.destroy_failed_jobs = true
+
+    # Every worker has a unique name which by default is the pid of the process.
+    # There are some advantages to overriding this with something which survives worker retarts:
+    # Workers can safely resume working on tasks which are locked by themselves. The worker will assume that it crashed before.
+    @@worker_name = nil
+
+    def self.worker_name
+      return @@worker_name unless @@worker_name.nil?
+      "host:#{Socket.gethostname} pid:#{Process.pid}" rescue "pid:#{Process.pid}"
+    end
+
+    def self.worker_name=(val)
+      @@worker_name = val
+    end
+
+    def worker_name
+      self.class.worker_name
+    end
+
+    def worker_name=(val)
+      @@worker_name = val
+    end
+
+    NextTaskSQL         = '(run_at <= ? AND (locked_at IS NULL OR locked_at < ?) OR (locked_by = ?)) AND failed_at IS NULL'
+    NextTaskOrder       = 'priority DESC, run_at ASC'
+
+    ParseObjectFromYaml = /\!ruby\/\w+\:([^\s]+)/
+
+    cattr_accessor :min_priority, :max_priority
+    self.min_priority = nil
+    self.max_priority = nil
+
+    # When a worker is exiting, make sure we don't have any locked jobs.
+    def self.clear_locks!
+      update_all("locked_by = null, locked_at = null", ["locked_by = ?", worker_name])
+    end
+
+    def failed?
+      failed_at
+    end
+    alias_method :failed, :failed?
+
+    def payload_object
+      @payload_object ||= deserialize(self['handler'])
+    end
+
+    def name
+      @name ||= begin
+        payload = payload_object
+        if payload.respond_to?(:display_name)
+          payload.display_name
+        else
+          payload.class.name
+        end
+      end
+    end
+
+    def payload_object=(object)
+      self['handler'] = object.to_yaml
+    end
+
+    # Reschedule the job in the future (when a job fails).
+    # Uses an exponential scale depending on the number of failed attempts.
+    def reschedule(message, backtrace = [], time = nil)
+      self.last_error   = message + "\n" + backtrace.join("\n")
+
+      if (self.attempts += 1) < max_attempts
+        time ||= Job.db_time_now + (attempts ** 4) + 5
+
+        self.run_at       = time
+        self.unlock
+        save!
+      else
+        logger.info "* [JOB] PERMANENTLY removing #{self.name} because of #{attempts} consecutive failures."
+        destroy_failed_jobs ? destroy : update_attribute(:failed_at, Delayed::Job.db_time_now)
+      end
+    end
+
+
+    # Try to run one job. Returns true/false (work done/work failed) or nil if job can't be locked.
+    def run_with_lock(max_run_time, worker_name)
+      logger.info "* [JOB] acquiring lock on #{name}"
+      unless lock_exclusively!(max_run_time, worker_name)
+        # We did not get the lock, some other worker process must have
+        logger.warn "* [JOB] failed to acquire exclusive lock for #{name}"
+        return nil # no work done
+      end
+
+      begin
+        runtime =  Benchmark.realtime do
+          Timeout.timeout(max_run_time.to_i) { invoke_job }
+          destroy
+        end
+        # TODO: warn if runtime > max_run_time ?
+        logger.info "* [JOB] #{name} completed after %.4f" % runtime
+        return true  # did work
+      rescue Exception => e
+        reschedule e.message, e.backtrace
+        log_exception(e)
+        return false  # work failed
+      end
+    end
+
+    # Add a job to the queue
+    def self.enqueue(*args, &block)
+      object = block_given? ? EvaledJob.new(&block) : args.shift
+
+      unless object.respond_to?(:perform) || block_given?
+        raise ArgumentError, 'Cannot enqueue items which do not respond to perform'
+      end
+
+      priority = args.first || 0
+      run_at   = args[1]
+
+      Job.create(:payload_object => object, :priority => priority.to_i, :run_at => run_at)
+    end
+
+    # Find a few candidate jobs to run (in case some immediately get locked by others).
+    def self.find_available(limit = 5, max_run_time = max_run_time)
+
+      time_now = db_time_now
+
+      sql = NextTaskSQL.dup
+
+      conditions = [time_now, time_now - max_run_time, worker_name]
+
+      if self.min_priority
+        sql << ' AND (priority >= ?)'
+        conditions << min_priority
+      end
+
+      if self.max_priority
+        sql << ' AND (priority <= ?)'
+        conditions << max_priority
+      end
+
+      conditions.unshift(sql)
+
+      ActiveRecord::Base.silence do
+        find(:all, :conditions => conditions, :order => NextTaskOrder, :limit => limit)
+      end
+    end
+
+    # Run the next job we can get an exclusive lock on.
+    # If no jobs are left we return nil
+    def self.reserve_and_run_one_job(max_run_time = max_run_time)
+
+      # We get up to 5 jobs from the db. In case we cannot get exclusive access to a job we try the next.
+      # this leads to a more even distribution of jobs across the worker processes
+      find_available(5, max_run_time).each do |job|
+        t = job.run_with_lock(max_run_time, worker_name)
+        return t unless t == nil  # return if we did work (good or bad)
+      end
+
+      nil # we didn't do any work, all 5 were not lockable
+    end
+
+    # Lock this job for this worker.
+    # Returns true if we have the lock, false otherwise.
+    def lock_exclusively!(max_run_time, worker = worker_name)
+      now = self.class.db_time_now
+      affected_rows = if locked_by != worker
+        # We don't own this job so we will update the locked_by name and the locked_at
+        self.class.update_all(["locked_at = ?, locked_by = ?", now, worker], ["id = ? and (locked_at is null or locked_at < ?) and (run_at <= ?)", id, (now - max_run_time.to_i), now])
+      else
+        # We already own this job, this may happen if the job queue crashes.
+        # Simply resume and update the locked_at
+        self.class.update_all(["locked_at = ?", now], ["id = ? and locked_by = ?", id, worker])
+      end
+      if affected_rows == 1
+        self.locked_at    = now
+        self.locked_by    = worker
+        return true
+      else
+        return false
+      end
+    end
+
+    # Unlock this job (note: not saved to DB)
+    def unlock
+      self.locked_at    = nil
+      self.locked_by    = nil
+    end
+
+    # This is a good hook if you need to report job processing errors in additional or different ways
+    def log_exception(error)
+      logger.error "* [JOB] #{name} failed with #{error.class.name}: #{error.message} - #{attempts} failed attempts"
+      logger.error(error)
+    end
+
+    # Do num jobs and return stats on success/failure.
+    # Exit early if interrupted.
+    def self.work_off(num = 100)
+      success, failure = 0, 0
+
+      num.times do
+        case self.reserve_and_run_one_job
+        when true
+            success += 1
+        when false
+            failure += 1
+        else
+          break  # leave if no work could be done
+        end
+        break if $exit # leave if we're exiting
+      end
+
+      return [success, failure]
+    end
+
+    # Moved into its own method so that new_relic can trace it.
+    def invoke_job
+      payload_object.perform
+    end
+
+  private
+
+    def deserialize(source)
+      handler = YAML.load(source) rescue nil
+
+      unless handler.respond_to?(:perform)
+        if handler.nil? && source =~ ParseObjectFromYaml
+          handler_class = $1
+        end
+        attempt_to_load(handler_class || handler.class)
+        handler = YAML.load(source)
+      end
+
+      return handler if handler.respond_to?(:perform)
+
+      raise DeserializationError,
+        'Job failed to load: Unknown handler. Try to manually require the appropriate file.'
+    rescue TypeError, LoadError, NameError => e
+      raise DeserializationError,
+        "Job failed to load: #{e.message}. Try to manually require the required file."
+    end
+
+    # Constantize the object so that ActiveSupport can attempt
+    # its auto loading magic. Will raise LoadError if not successful.
+    def attempt_to_load(klass)
+       klass.constantize
+    end
+
+    # Get the current time (GMT or local depending on DB)
+    # Note: This does not ping the DB to get the time, so all your clients
+    # must have syncronized clocks.
+    def self.db_time_now
+      if (defined? Time.zone) && Time.zone
+        Time.zone.now
+      elsif ActiveRecord::Base.default_timezone == :utc
+        Time.now.utc
+      else
+        Time.now
+      end
+    end
+
+  protected
+
+    def before_save
+      self.run_at ||= self.class.db_time_now
+    end
+
+  end
+
+  class EvaledJob
+    def initialize
+      @job = yield
+    end
+
+    def perform
+      eval(@job)
+    end
+  end
+end

data/lib/delayed/message_sending.rb

@@ -0,0 +1,22 @@
+module Delayed
+  module MessageSending
+    def send_later(method, *args)
+      Delayed::Job.enqueue Delayed::PerformableMethod.new(self, method.to_sym, args)
+    end
+
+    def send_at(time, method, *args)
+      Delayed::Job.enqueue(Delayed::PerformableMethod.new(self, method.to_sym, args), 0, time)
+    end
+    
+    module ClassMethods
+      def handle_asynchronously(method)
+        aliased_method, punctuation = method.to_s.sub(/([?!=])$/, ''), $1
+        with_method, without_method = "#{aliased_method}_with_send_later#{punctuation}", "#{aliased_method}_without_send_later#{punctuation}"
+        define_method(with_method) do |*args|
+          send_later(without_method, *args)
+        end
+        alias_method_chain method, :send_later
+      end
+    end
+  end                               
+end

data/lib/delayed/performable_method.rb

@@ -0,0 +1,55 @@
+module Delayed
+  class PerformableMethod < Struct.new(:object, :method, :args)
+    CLASS_STRING_FORMAT = /^CLASS\:([A-Z][\w\:]+)$/
+    AR_STRING_FORMAT    = /^AR\:([A-Z][\w\:]+)\:(\d+)$/
+
+    def initialize(object, method, args)
+      raise NoMethodError, "undefined method `#{method}' for #{object.inspect}" unless object.respond_to?(method)
+
+      self.object = dump(object)
+      self.args   = args.map { |a| dump(a) }
+      self.method = method.to_sym
+    end
+    
+    def display_name  
+      case self.object
+      when CLASS_STRING_FORMAT then "#{$1}.#{method}"
+      when AR_STRING_FORMAT    then "#{$1}##{method}"
+      else "Unknown##{method}"
+      end      
+    end    
+
+    def perform
+      load(object).send(method, *args.map{|a| load(a)})
+    rescue ActiveRecord::RecordNotFound
+      # We cannot do anything about objects which were deleted in the meantime
+      true
+    end
+
+    private
+
+    def load(arg)
+      case arg
+      when CLASS_STRING_FORMAT then $1.constantize
+      when AR_STRING_FORMAT    then $1.constantize.find($2)
+      else arg
+      end
+    end
+
+    def dump(arg)
+      case arg
+      when Class              then class_to_string(arg)
+      when ActiveRecord::Base then ar_to_string(arg)
+      else arg
+      end
+    end
+
+    def ar_to_string(obj)
+      "AR:#{obj.class}:#{obj.id}"
+    end
+
+    def class_to_string(obj)
+      "CLASS:#{obj.name}"
+    end
+  end
+end

data/lib/delayed/recipes.rb

@@ -0,0 +1,31 @@
+# Capistrano Recipes for managing delayed_job
+#
+# Add these callbacks to have the delayed_job process restart when the server
+# is restarted:
+#
+#   after "deploy:stop",    "delayed_job:stop"
+#   after "deploy:start",   "delayed_job:start"
+#   after "deploy:restart", "delayed_job:restart"
+
+Capistrano::Configuration.instance.load do
+  namespace :delayed_job do
+    def rails_env
+      fetch(:rails_env, false) ? "RAILS_ENV=#{fetch(:rails_env)}" : ''
+    end
+    
+    desc "Stop the delayed_job process"
+    task :stop, :roles => :app do
+      run "cd #{current_path};#{rails_env} script/delayed_job stop"
+    end
+
+    desc "Start the delayed_job process"
+    task :start, :roles => :app do
+      run "cd #{current_path};#{rails_env} script/delayed_job start"
+    end
+
+    desc "Restart the delayed_job process"
+    task :restart, :roles => :app do
+      run "cd #{current_path};#{rails_env} script/delayed_job restart"
+    end
+  end
+end

data/lib/delayed/tasks.rb

@@ -0,0 +1,15 @@
+# Re-definitions are appended to existing tasks
+task :environment
+task :merb_env
+
+namespace :jobs do
+  desc "Clear the delayed_job queue."
+  task :clear => [:merb_env, :environment] do
+    Delayed::Job.delete_all
+  end
+
+  desc "Start a delayed_job worker."
+  task :work => [:merb_env, :environment] do
+    Delayed::Worker.new(:min_priority => ENV['MIN_PRIORITY'], :max_priority => ENV['MAX_PRIORITY']).start
+  end
+end

data/lib/delayed/worker.rb

@@ -0,0 +1,77 @@
+module Delayed
+  class Worker
+    @@sleep_delay = 5
+
+    cattr_accessor :sleep_delay
+
+    cattr_accessor :logger
+    self.logger = if defined?(Merb::Logger)
+      Merb.logger
+    elsif defined?(RAILS_DEFAULT_LOGGER)
+      RAILS_DEFAULT_LOGGER
+    end
+
+    # name_prefix is ignored if name is set directly
+    attr_accessor :name_prefix
+
+    def job_max_run_time
+      Delayed::Job.max_run_time
+    end
+
+    # Every worker has a unique name which by default is the pid of the process.
+    # There are some advantages to overriding this with something which survives worker retarts:
+    # Workers can safely resume working on tasks which are locked by themselves. The worker will assume that it crashed before.
+    def name
+      return @name unless @name.nil?
+      "#{@name_prefix}host:#{Socket.gethostname} pid:#{Process.pid}" rescue "#{@name_prefix}pid:#{Process.pid}"
+    end
+
+    # Sets the name of the worker.
+    # Setting the name to nil will reset the default worker name
+    def name=(val)
+      @name = val
+    end
+
+    def initialize(options={})
+      @quiet = options[:quiet]
+      Delayed::Job.min_priority = options[:min_priority] if options.has_key?(:min_priority)
+      Delayed::Job.max_priority = options[:max_priority] if options.has_key?(:max_priority)
+    end
+
+    def start
+      say "*** Starting job worker #{Delayed::Job.worker_name}"
+
+      trap('TERM') { say 'Exiting...'; $exit = true }
+      trap('INT')  { say 'Exiting...'; $exit = true }
+
+      loop do
+        result = nil
+
+        realtime = Benchmark.realtime do
+          result = Delayed::Job.work_off
+        end
+
+        count = result.sum
+
+        break if $exit
+
+        if count.zero?
+          sleep(@@sleep_delay)
+        else
+          say "#{count} jobs processed at %.4f j/s, %d failed ..." % [count / realtime, result.last]
+        end
+
+        break if $exit
+      end
+
+    ensure
+      Delayed::Job.clear_locks!
+    end
+
+    def say(text)
+      puts text unless @quiet
+      logger.info text if logger
+    end
+
+  end
+end