logstash-integration-jdbc 5.2.6 → 5.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c9cc41a07a8cb2f7e4b9a6993dd4d0cd69761b3fa95ba81238d0dd6267367311
-  data.tar.gz: 32866a340d87d91734586b3324a1349437abc624deb6ff9883ab998b0a4524a6
+  metadata.gz: d9937a8c1c5ab26acb4cd887f4bdb9dfff51e9348c7187ef2d44ff6055d137ee
+  data.tar.gz: 0042c3e29b5b08abe8baa4f84e4c240960bbc615778df9c77415f8db7985c831
 SHA512:
-  metadata.gz: b3513ba2d9ade38a829ec0b0c47ad6c0978d0256e03fb4ac26e136a064db65b08a19b7ee8dd7dabe26851739877b82f0f9a550b2328473b8ffd62f194d569ebb
-  data.tar.gz: bf71a208f07bc00c213724cbcf175a9ede2f87bf4eaf85a926ee8e9f87b322e2dd79164db1db84ec60633a0b1cfa961e8fc6d3889c8ca25ea220fa437285af5d
+  metadata.gz: dbc38871c106b045a500645cf6c4517b30ce15e52bfc68520845e22276efdb4a21df3e4a7709ae682cd6b55ff76e063a615b9fe397795272535aa7c5298a9a92
+  data.tar.gz: 70b8e1dc84ba60d478affb22c93400cb153d4d0adc4904667970220ac03cb9d22b94e28f1b1a5504a30b8592c543d3234ee441d0ed57a31aefef70dfb6c2b9a3

data/CHANGELOG.md

@@ -1,3 +1,6 @@
+## 5.3.0
+  - Refactor: start using scheduler mixin [#110](https://github.com/logstash-plugins/logstash-integration-jdbc/pull/110)
+
 ## 5.2.6
   - Fix: change default path of 'last_run_metadata_path' to be rooted in the LS data.path folder and not in $HOME [#106](https://github.com/logstash-plugins/logstash-integration-jdbc/pull/106)
 

data/lib/logstash/filters/jdbc_static.rb

@@ -3,7 +3,7 @@ require "logstash-integration-jdbc_jars"
 require "logstash/filters/base"
 require "logstash/namespace"
 require "logstash/plugin_mixins/ecs_compatibility_support"
-require "logstash/plugin_mixins/jdbc/scheduler"
+require "logstash/plugin_mixins/scheduler"
 require_relative "jdbc/loader"
 require_relative "jdbc/loader_schedule"
 require_relative "jdbc/repeating_load_runner"
@@ -19,6 +19,8 @@ module LogStash module Filters class JdbcStatic < LogStash::Filters::Base
   # adds ecs_compatibility config which could be :disabled or :v1
   include LogStash::PluginMixins::ECSCompatibilitySupport(:disabled, :v1, :v8 => :v1)
 
+  include LogStash::PluginMixins::Scheduler
+
   config_name "jdbc_static"
 
   # Define the loaders, an Array of Hashes, to fetch remote data and create local tables.
@@ -162,7 +164,6 @@ module LogStash module Filters class JdbcStatic < LogStash::Filters::Base
   end
 
   def close
-    @scheduler.stop if @scheduler
     @parsed_loaders.each(&:close)
     @processor.close
   end
@@ -208,13 +209,7 @@ module LogStash module Filters class JdbcStatic < LogStash::Filters::Base
     if @loader_schedule
       @loader_runner = Jdbc::RepeatingLoadRunner.new(*runner_args)
       @loader_runner.initial_load
-      @scheduler = LogStash::PluginMixins::Jdbc::Scheduler.
-          start_cron_scheduler(@loader_schedule, thread_name: "[#{id}]-jdbc_static__scheduler") { @loader_runner.repeated_load }
-      cron_job = @scheduler.cron_jobs.first
-      if cron_job
-        frequency = cron_job.respond_to?(:rough_frequency) ? cron_job.rough_frequency : cron_job.frequency
-        logger.info("Loaders will execute every #{frequency} seconds", loader_schedule: @loader_schedule)
-      end
+      scheduler.cron(@loader_schedule) { @loader_runner.repeated_load }
     else
       @loader_runner = Jdbc::SingleLoadRunner.new(*runner_args)
       @loader_runner.initial_load

data/lib/logstash/inputs/jdbc.rb

@@ -3,12 +3,11 @@ require "logstash/inputs/base"
 require "logstash/namespace"
 require "logstash/plugin_mixins/jdbc/common"
 require "logstash/plugin_mixins/jdbc/jdbc"
-require "logstash/plugin_mixins/jdbc/scheduler"
 require "logstash/plugin_mixins/ecs_compatibility_support"
 require "logstash/plugin_mixins/ecs_compatibility_support/target_check"
 require "logstash/plugin_mixins/validator_support/field_reference_validation_adapter"
-
 require "logstash/plugin_mixins/event_support/event_factory_adapter"
+require "logstash/plugin_mixins/scheduler"
 require "fileutils"
 
 # this require_relative returns early unless the JRuby version is between 9.2.0.0 and 9.2.8.0
@@ -147,6 +146,8 @@ module LogStash module Inputs class Jdbc < LogStash::Inputs::Base
   # adds :field_reference validator adapter
   extend LogStash::PluginMixins::ValidatorSupport::FieldReferenceValidationAdapter
 
+  include LogStash::PluginMixins::Scheduler
+
   config_name "jdbc"
 
   # If undefined, Logstash will complain, even if codec is unused.
@@ -260,7 +261,6 @@ module LogStash module Inputs class Jdbc < LogStash::Inputs::Base
       end
     end
 
-    require "rufus/scheduler"
     prepare_jdbc_connection
 
     if @use_column_value
@@ -319,22 +319,16 @@ module LogStash module Inputs class Jdbc < LogStash::Inputs::Base
   def run(queue)
     load_driver
     if @schedule
-      # input thread (Java) name example "[my-oracle]<jdbc"
-      @scheduler = LogStash::PluginMixins::Jdbc::Scheduler.
-          start_cron_scheduler(@schedule, thread_name: "[#{id}]<jdbc__scheduler") { execute_query(queue) }
-      @scheduler.join
+      # scheduler input thread name example: "[my-oracle]|input|jdbc|scheduler"
+      scheduler.cron(@schedule) { execute_query(queue) }
+      scheduler.join
     else
       execute_query(queue)
     end
   end # def run
 
-  def close
-    @scheduler.shutdown if @scheduler
-  end
-
   def stop
     close_jdbc_connection
-    @scheduler.shutdown(:wait) if @scheduler
   end
 
   private

data/logstash-integration-jdbc.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name = 'logstash-integration-jdbc'
-  s.version         = '5.2.6'
+  s.version         = '5.3.0'
   s.licenses = ['Apache License (2.0)']
   s.summary         = "Integration with JDBC - input and filter plugins"
   s.description     = "This gem is a Logstash plugin required to be installed on top of the Logstash core pipeline using $LS_HOME/bin/logstash-plugin install gemname. This gem is not a stand-alone program"
@@ -34,12 +34,11 @@ Gem::Specification.new do |s|
 
   s.add_runtime_dependency 'tzinfo'
   s.add_runtime_dependency 'tzinfo-data'
-  # plugin maintains compatibility with < 3.5 (3.0.9)
-  # but works with newer rufus-scheduler >= 3.5 as well
-  s.add_runtime_dependency 'rufus-scheduler'
+
   s.add_runtime_dependency 'logstash-mixin-ecs_compatibility_support', '~>1.3'
   s.add_runtime_dependency "logstash-mixin-validator_support", '~> 1.0'
   s.add_runtime_dependency "logstash-mixin-event_support", '~> 1.0'
+  s.add_runtime_dependency "logstash-mixin-scheduler", '~> 1.0'
 
   s.add_development_dependency "childprocess"
   s.add_development_dependency 'logstash-devutils', '>= 2.3'

data/spec/inputs/jdbc_spec.rb

@@ -251,18 +251,6 @@ describe LogStash::Inputs::Jdbc do
       Timecop.return
     end
 
-    it "cleans up scheduler resources on close" do
-      runner = Thread.new do
-        plugin.run(queue)
-      end
-      sleep 1
-      plugin.do_close
-
-      scheduler = plugin.instance_variable_get(:@scheduler)
-      expect(scheduler).to_not be_nil
-      expect(scheduler.down?).to be_truthy
-    end
-
   end
 
   context "when scheduling and previous runs are to be preserved" do
@@ -1717,7 +1705,7 @@ describe LogStash::Inputs::Jdbc do
       let(:jdbc_driver_class) { "org.apache.NonExistentDriver" }
       it "raises a loading error" do
         expect { plugin.send(:load_driver) }.to raise_error LogStash::PluginLoadingError,
-                                                            /java.lang.ClassNotFoundException: org.apache.NonExistentDriver/
+                                                            /ClassNotFoundException: org.apache.NonExistentDriver/
       end
     end
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: logstash-integration-jdbc
 version: !ruby/object:Gem::Version
-  version: 5.2.6
+  version: 5.3.0
 platform: ruby
 authors:
 - Elastic
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-05-19 00:00:00.000000000 Z
+date: 2022-06-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
@@ -131,38 +131,38 @@ dependencies:
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
-  name: rufus-scheduler
+        version: '1.3'
+  name: logstash-mixin-ecs_compatibility_support
   prerelease: false
   type: :runtime
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.3'
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.3'
-  name: logstash-mixin-ecs_compatibility_support
+        version: '1.0'
+  name: logstash-mixin-validator_support
   prerelease: false
   type: :runtime
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.3'
+        version: '1.0'
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.0'
-  name: logstash-mixin-validator_support
+  name: logstash-mixin-event_support
   prerelease: false
   type: :runtime
   version_requirements: !ruby/object:Gem::Requirement
@@ -176,7 +176,7 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.0'
-  name: logstash-mixin-event_support
+  name: logstash-mixin-scheduler
   prerelease: false
   type: :runtime
   version_requirements: !ruby/object:Gem::Requirement
@@ -277,7 +277,6 @@ files:
 - lib/logstash/inputs/tzinfo_jruby_patch.rb
 - lib/logstash/plugin_mixins/jdbc/common.rb
 - lib/logstash/plugin_mixins/jdbc/jdbc.rb
-- lib/logstash/plugin_mixins/jdbc/scheduler.rb
 - lib/logstash/plugin_mixins/jdbc/statement_handler.rb
 - lib/logstash/plugin_mixins/jdbc/value_tracking.rb
 - lib/logstash/plugin_mixins/jdbc_streaming.rb
@@ -306,7 +305,6 @@ files:
 - spec/helpers/derbyrun.jar
 - spec/inputs/integration/integ_spec.rb
 - spec/inputs/jdbc_spec.rb
-- spec/plugin_mixins/jdbc/scheduler_spec.rb
 - spec/plugin_mixins/jdbc_streaming/parameter_handler_spec.rb
 - vendor/jar-dependencies/org/apache/derby/derby/10.14.1.0/derby-10.14.1.0.jar
 - vendor/jar-dependencies/org/apache/derby/derbyclient/10.14.1.0/derbyclient-10.14.1.0.jar
@@ -359,5 +357,4 @@ test_files:
 - spec/helpers/derbyrun.jar
 - spec/inputs/integration/integ_spec.rb
 - spec/inputs/jdbc_spec.rb
-- spec/plugin_mixins/jdbc/scheduler_spec.rb
 - spec/plugin_mixins/jdbc_streaming/parameter_handler_spec.rb

data/lib/logstash/plugin_mixins/jdbc/scheduler.rb

@@ -1,175 +0,0 @@
-require 'rufus/scheduler'
-
-require 'logstash/util/loggable'
-
-module LogStash module PluginMixins module Jdbc
-  class Scheduler < Rufus::Scheduler
-
-    include LogStash::Util::Loggable
-
-    # Rufus::Scheduler >= 3.4 moved the Time impl into a gem EoTime = ::EtOrbi::EoTime`
-    # Rufus::Scheduler 3.1 - 3.3 using it's own Time impl `Rufus::Scheduler::ZoTime`
-    TimeImpl = defined?(Rufus::Scheduler::EoTime) ? Rufus::Scheduler::EoTime :
-                   (defined?(Rufus::Scheduler::ZoTime) ? Rufus::Scheduler::ZoTime : ::Time)
-
-    # @param cron [String] cron-line
-    # @param opts [Hash] scheduler options
-    # @return scheduler instance
-    def self.start_cron_scheduler(cron, opts = {}, &block)
-      unless block_given?
-        raise ArgumentError, 'missing (cron scheduler) block - worker task to execute'
-      end
-      scheduler = new_scheduler(opts)
-      scheduler.schedule_cron(cron, &block)
-      scheduler
-    end
-
-    # @param opts [Hash] scheduler options
-    # @return scheduler instance
-    def self.new_scheduler(opts)
-      unless opts.key?(:thread_name)
-        raise ArgumentError, 'thread_name: option is required to be able to distinguish multiple scheduler threads'
-      end
-      opts[:max_work_threads] ||= 1
-      # amount the scheduler thread sleeps between checking whether jobs
-      # should trigger, default is 0.3 which is a bit too often ...
-      # in theory the cron expression '* * * * * *' supports running jobs
-      # every second but this is very rare, we could potentially go higher
-      opts[:frequency] ||= 1.0
-
-      new(opts)
-    end
-
-    # @overload
-    def timeout_jobs
-      # Rufus relies on `Thread.list` which is a blocking operation and with many schedulers
-      # (and threads) within LS will have a negative impact on performance as scheduler
-      # threads will end up waiting to obtain the `Thread.list` lock.
-      #
-      # However, this isn't necessary we can easily detect whether there are any jobs
-      # that might need to timeout: only when `@opts[:timeout]` is set causes worker thread(s)
-      # to have a `Thread.current[:rufus_scheduler_timeout]` that is not nil
-      return unless @opts[:timeout]
-      super
-    end
-
-    # @overload
-    def work_threads(query = :all)
-      if query == :__all_no_cache__ # special case from JobDecorator#start_work_thread
-        @_work_threads = nil # when a new worker thread is being added reset
-        return super(:all)
-      end
-
-      # Gets executed every time a job is triggered, we're going to cache the
-      # worker threads for this scheduler (to avoid `Thread.list`) - they only
-      # change when a new thread is being started from #start_work_thread ...
-      work_threads = @_work_threads
-      if work_threads.nil?
-        work_threads = threads.select { |t| t[:rufus_scheduler_work_thread] }
-        @_work_threads = work_threads
-      end
-
-      case query
-      when :active then work_threads.select { |t| t[:rufus_scheduler_job] }
-      when :vacant then work_threads.reject { |t| t[:rufus_scheduler_job] }
-      else work_threads
-      end
-    end
-
-    # @overload
-    def on_error(job, err)
-      details = { exception: err.class, message: err.message, backtrace: err.backtrace }
-      details[:cause] = err.cause if err.cause
-
-      details[:now] = debug_format_time(TimeImpl.now)
-      details[:last_time] = (debug_format_time(job.last_time) rescue nil)
-      details[:next_time] = (debug_format_time(job.next_time) rescue nil)
-      details[:job] = job
-
-      details[:opts] = @opts
-      details[:started_at] = started_at
-      details[:thread] = thread.inspect
-      details[:jobs_size] = @jobs.size
-      details[:work_threads_size] = work_threads.size
-      details[:work_queue_size] = work_queue.size
-
-      logger.error("Scheduler intercepted an error:", details)
-
-    rescue => e
-      logger.error("Scheduler failed in #on_error #{e.inspect}")
-    end
-
-    def debug_format_time(time)
-      # EtOrbi::EoTime used by (newer) Rufus::Scheduler has to_debug_s https://git.io/JyiPj
-      time.respond_to?(:to_debug_s) ? time.to_debug_s : time.strftime("%Y-%m-%dT%H:%M:%S.%L")
-    end
-    private :debug_format_time
-
-    # @private helper used by JobDecorator
-    def work_thread_name_prefix
-      ( @opts[:thread_name] || "#{@thread_key}_scheduler" ) + '_worker-'
-    end
-
-    protected
-
-    # @overload
-    def start
-      ret = super() # @thread[:name] = @opts[:thread_name] || "#{@thread_key}_scheduler"
-
-      # at least set thread.name for easier thread dump analysis
-      if @thread.is_a?(Thread) && @thread.respond_to?(:name=)
-        @thread.name = @thread[:name] if @thread[:name]
-      end
-
-      ret
-    end
-
-    # @overload
-    def do_schedule(job_type, t, callable, opts, return_job_instance, block)
-      job_or_id = super
-
-      job_or_id.extend JobDecorator if return_job_instance
-
-      job_or_id
-    end
-
-    module JobDecorator
-
-      def start_work_thread
-        prev_thread_count = @scheduler.work_threads.size
-
-        ret = super() # does not return Thread instance in 3.0
-
-        work_threads = @scheduler.work_threads(:__all_no_cache__)
-        while prev_thread_count == work_threads.size # very unlikely
-          Thread.pass
-          work_threads = @scheduler.work_threads(:__all_no_cache__)
-        end
-
-        work_thread_name_prefix = @scheduler.work_thread_name_prefix
-
-        work_threads.sort! do |t1, t2|
-          if t1[:name].nil?
-            t2[:name].nil? ? 0 : +1 # nils at the end
-          elsif t2[:name].nil?
-            t1[:name].nil? ? 0 : -1
-          else
-            t1[:name] <=> t2[:name]
-          end
-        end
-
-        work_threads.each_with_index do |thread, i|
-          unless thread[:name]
-            thread[:name] = "#{work_thread_name_prefix}#{sprintf('%02i', i)}"
-            thread.name = thread[:name] if thread.respond_to?(:name=)
-            # e.g. "[oracle]<jdbc_scheduler_worker-00"
-          end
-        end
-
-        ret
-      end
-
-    end
-
-  end
-end end end

data/spec/plugin_mixins/jdbc/scheduler_spec.rb

@@ -1,78 +0,0 @@
-# encoding: utf-8
-require "logstash/devutils/rspec/spec_helper"
-require "logstash/plugin_mixins/jdbc/scheduler"
-
-describe LogStash::PluginMixins::Jdbc::Scheduler do
-
-  let(:thread_name) { '[test]<jdbc_scheduler' }
-
-  let(:opts) do
-    { :max_work_threads => 2, :thread_name => thread_name }
-  end
-
-  subject(:scheduler) { LogStash::PluginMixins::Jdbc::Scheduler.new(opts) }
-
-  after { scheduler.stop(:wait) }
-
-  it "sets scheduler thread name" do
-    expect( scheduler.thread.name ).to include thread_name
-  end
-
-  context 'cron schedule' do
-
-    before do
-      scheduler.schedule_cron('* * * * * *') { sleep 1.25 } # every second
-    end
-
-    it "sets worker thread names" do
-      sleep 3.0
-      threads = scheduler.work_threads
-      threads.sort! { |t1, t2| (t1.name || '') <=> (t2.name || '') }
-
-      expect( threads.size ).to eql 2
-      expect( threads.first.name ).to eql "#{thread_name}_worker-00"
-      expect( threads.last.name ).to eql "#{thread_name}_worker-01"
-    end
-
-  end
-
-  context 'every 1s' do
-
-    before do
-      scheduler.schedule_in('1s') { raise 'TEST' } # every second
-    end
-
-    it "logs errors handled" do
-      expect( scheduler.logger ).to receive(:error).with /Scheduler intercepted an error/, hash_including(:message => 'TEST')
-      sleep 1.5
-    end
-
-  end
-
-  context 'work threads' do
-
-    let(:opts) { super().merge :max_work_threads => 3 }
-
-    let(:counter) { java.util.concurrent.atomic.AtomicLong.new(0) }
-
-    before do
-      scheduler.schedule_cron('* * * * * *') { counter.increment_and_get; sleep 3.25 } # every second
-    end
-
-    it "are working" do
-      sleep(0.05) while counter.get == 0
-      expect( scheduler.work_threads.size ).to eql 1
-      sleep(0.05) while counter.get == 1
-      expect( scheduler.work_threads.size ).to eql 2
-      sleep(0.05) while counter.get == 2
-      expect( scheduler.work_threads.size ).to eql 3
-
-      sleep 1.25
-      expect( scheduler.work_threads.size ).to eql 3
-      sleep 1.25
-      expect( scheduler.work_threads.size ).to eql 3
-    end
-
-  end
-
-end