logstash-output-azure_loganalytics 0.5.2 → 0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: f5703dcf7467f52e043faed81a31e4ac16326a28
-  data.tar.gz: a1626400b84f10787997929640fce9dcc51fad4e
+  metadata.gz: c8478ec73e02eae91388307f89026500b140364d
+  data.tar.gz: 8ca5e7e57bf454b4f33ff614b5f9e25a76b1ea1c
 SHA512:
-  metadata.gz: 63e25706eec6fad297468afd439ac9dd93c567d838f584124bc276d3568f663ae6923bf6b4fcff2d15caea3dcde26b067ba788db5a3bf4203f0789d3e321bf92
-  data.tar.gz: b2492d86bbcd2ac2aaf00c6274bc6d039a19f256e557026f3a6b011df45a53e798583b48d1c65f1c7f6a2d9bf69187516f250a2feaef9127f03beb851deffd32
+  metadata.gz: cf96615306ab45d89fa999a4ded0ed0da8f31e5b6caf01b1d473b57a36f16303d04211eda349944a27badd93fcea4da0fa632795eedb5b385ceb835f7b2448fa
+  data.tar.gz: d0762a739e1f30b70a0cf1084cdbfabdd75cea7ce6851eef6847e09d71543bb8bec9237a21e20fc8eea39a2213ea6367d6ca5d678244b5a31734312a111c9e9f

data/CHANGELOG.md

@@ -1,3 +1,10 @@
+## 0.6.0
+
+* Multithreading support - [PR #17](https://github.com/yokawasa/logstash-output-azure_loganalytics/pull/17) by [@daniel-chambers](https://github.com/daniel-chambers)
+  * Big performance improvement
+  * New parame `max_batch_items` is added
+  * No longer `flush_items` and `flush_interval_time` params are supported in the plugin configuration
+
 ## 0.5.2
 
 * Fixed using sprintf in log_type - [PR #16](https://github.com/yokawasa/logstash-output-azure_loganalytics/pull/16) by [@daniel-chambers](https://github.com/daniel-chambers)

data/README.md

@@ -1,6 +1,13 @@
 # Azure Log Analytics output plugin for Logstash 
 logstash-output-azure_loganalytics is a logstash plugin to output to Azure Log Analytics. [Logstash](https://www.elastic.co/products/logstash) is an open source, server-side data processing pipeline that ingests data from a multitude of sources simultaneously, transforms it, and then sends it to your favorite [destinations](https://www.elastic.co/products/logstash). [Log Analytics](https://azure.microsoft.com/en-us/services/log-analytics/) is a service in Operations Management Suite (OMS) that helps you collect and analyze data generated by resources in your cloud and on-premises environments. It gives you real-time insights using integrated search and custom dashboards to readily analyze millions of records across all of your workloads and servers regardless of their physical location. The plugin stores in-coming events to Azure Log Analytics by leveraging [Log Analytics HTTP Data Collector API](https://docs.microsoft.com/en-us/azure/log-analytics/log-analytics-data-collector-api)
 
+> [NOTICE]
+> logstash-output-azure_loganalytics >= 0.6.0
+> - Multithreading support   
+> - New parame `max_batch_items` is added
+> - No longer `flush_items` and `flush_interval_time` params are supported in the plugin configuration
+
+
 ## Installation
 
 You can install this plugin using the Logstash "plugin" or "logstash-plugin" (for newer versions of Logstash) command:
@@ -21,8 +28,7 @@ output {
         log_type => "<LOG TYPE NAME>"
         key_names  => ['key1','key2','key3'..] ## list of Key names
         key_types => {'key1'=> 'string' 'key2'=>'double' 'key3'=>'boolean' .. }
-        flush_items => <FLUSH_ITEMS_NUM>
-        flush_interval_time => <FLUSH INTERVAL TIME(sec)>
+        max_batch_items => <MAX BATCH ITEMS (num)>
     }
 }
 ```
@@ -37,8 +43,7 @@ output {
    * Multiple key value entries are separated by `spaces` rather than commas (See also [this](https://www.elastic.co/guide/en/logstash/current/configuration-file-structure.html#hash))
    * If you want to store a column as datetime or guid data format, set `string` for the column ( the value of the column should be `YYYY-MM-DDThh:mm:ssZ format` if it's `datetime`, and `GUID format` if it's `guid`).
    * In case that `key_types` param are not specified, all columns that you want to submit ( you choose with `key_names` param ) are stored as `string` data type in Log Analytics.
- * **flush_items (optional)** - Default 50. Max number of items to buffer before flushing (1 - 1000).
- * **flush_interval_time (optional)** - Default 5. Max number of seconds to wait between flushes.
+ * **max_batch_items (optional)** - Default 50. Maximum number of log events to put in one request to Log Analytics.
 
 > [NOTE] There is a special param for changing the Log Analytics API endpoint (mainly for supporting Azure sovereign cloud)
 > * **endpoint (optional)** - Default: ods.opinsights.azure.com 

data/VERSION

@@ -1 +1 @@
-0.5.2
+0.6.0

data/lib/logstash/outputs/azure_loganalytics.rb

@@ -2,11 +2,9 @@
 
 require "logstash/outputs/base"
 require "logstash/namespace"
-require "stud/buffer"
+require "securerandom"
 
 class LogStash::Outputs::AzureLogAnalytics < LogStash::Outputs::Base
-  include Stud::Buffer
-
   config_name "azure_loganalytics"
 
   # Your Operations Management Suite workspace ID
@@ -41,11 +39,10 @@ class LogStash::Outputs::AzureLogAnalytics < LogStash::Outputs::Base
   #   key_types => {'key1'=>'string' 'key2'=>'string' 'key3'=>'boolean' 'key4'=>'double' ...}
   config :key_types, :validate => :hash, :default => {}
 
-  # Max number of items to buffer before flushing. Default 50.
-  config :flush_items, :validate => :number, :default => 50
-  
-  # Max number of seconds to wait between flushes. Default 5
-  config :flush_interval_time, :validate => :number, :default => 5
+  # Maximum number of log events to put in one request to Log Analytics
+  config :max_batch_items, :validate => :number, :default => 50
+
+  concurrency :shared
 
   public
   def register
@@ -61,24 +58,14 @@ class LogStash::Outputs::AzureLogAnalytics < LogStash::Outputs::Base
     ## Start 
     @client=Azure::Loganalytics::Datacollectorapi::Client::new(@customer_id,@shared_key,@endpoint)
 
-    buffer_initialize(
-      :max_items => @flush_items,
-      :max_interval => @flush_interval_time,
-      :logger => @logger
-    )
-
   end # def register
 
   public
-  def receive(event)
-    # Simply save an event for later delivery
-    buffer_receive(event)
-  end # def receive
+  def multi_receive(events)
+    
+    flush_guid = SecureRandom.uuid
+    @logger.debug("Start receive: #{flush_guid}. Received #{events.length} events")
 
-  # called from Stud::Buffer#buffer_flush when there are events to flush
-  public
-  def flush (events, close=false)
-  
     documentsByLogType = {}  # This is a map of log_type to list of documents (themselves maps) to send to Log Analytics
     events.each do |event|
       document = {}
@@ -115,20 +102,23 @@ class LogStash::Outputs::AzureLogAnalytics < LogStash::Outputs::Base
     end
 
     documentsByLogType.each do |log_type_for_events, events|
-      begin
-        @logger.debug("Posting log batch (log count: #{events.length}) as log type #{log_type_for_events} to DataCollector API. First log: " + (events[0].to_json).to_s)
-        res = @client.post_data(log_type_for_events, events, @time_generated_field)
-        if Azure::Loganalytics::Datacollectorapi::Client.is_success(res)
-          @logger.debug("Successfully posted logs as log type #{log_type_for_events} with result code #{res.code} to DataCollector API")
-        else
-          @logger.error("DataCollector API request failure: error code: #{res.code}, data=>" + (events.to_json).to_s)
+      events.each_slice(@max_batch_items) do |event_batch|
+        begin
+          @logger.debug("Posting log batch (log count: #{event_batch.length}) as log type #{log_type_for_events} to DataCollector API. First log: " + (event_batch[0].to_json).to_s)
+          res = @client.post_data(log_type_for_events, event_batch, @time_generated_field)
+          if Azure::Loganalytics::Datacollectorapi::Client.is_success(res)
+            @logger.debug("Successfully posted logs as log type #{log_type_for_events} with result code #{res.code} to DataCollector API")
+          else
+            @logger.error("DataCollector API request failure (log type #{log_type_for_events}): error code: #{res.code}, data=>" + (event_batch.to_json).to_s)
+          end
+        rescue Exception => ex
+          @logger.error("Exception occured in posting to DataCollector API as log type #{log_type_for_events}: '#{ex}', data=>" + (event_batch.to_json).to_s)
         end
-      rescue Exception => ex
-        @logger.error("Exception occured in posting to DataCollector API: '#{ex}', data=>" + (events.to_json).to_s)
       end
     end
-    
-  end # def flush
+    @logger.debug("End receive: #{flush_guid}")
+
+  end # def multi_receive
 
   private
   def convert_value(type, val)

data/spec/outputs/azure_loganalytics_spec.rb

@@ -28,7 +28,7 @@ describe LogStash::Outputs::AzureLogAnalytics do
      azure_loganalytics_output.register
   end 
 
-  describe "#flush" do
+  describe "#multi_receive" do
     it "Should successfully send the event to Azure Log Analytics" do
       events = []
       log1 = {
@@ -61,11 +61,9 @@ describe LogStash::Outputs::AzureLogAnalytics do
 
       event1 =  LogStash::Event.new(log1) 
       event2 =  LogStash::Event.new(log2) 
-      azure_loganalytics_output.receive(event1)
-      azure_loganalytics_output.receive(event2)
       events.push(event1)
       events.push(event2)
-      expect {azure_loganalytics_output.flush(events)}.to_not raise_error
+      expect {azure_loganalytics_output.multi_receive(events)}.to_not raise_error
     end
   end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: logstash-output-azure_loganalytics
 version: !ruby/object:Gem::Version
-  version: 0.5.2
+  version: 0.6.0
 platform: ruby
 authors:
 - Yoichi Kawasaki
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-09-21 00:00:00.000000000 Z
+date: 2020-10-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement