logstash-output-scalyr 0.1.9 → 0.1.14.beta

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 542910023101687e2d9bce1d355f3353a9f9eab2dbc8190ae47c948b17b1db58
-  data.tar.gz: 478acd0ae33f8b102da138ecfebe3a1ecab68f7d4b2d3779695812184e7a5618
+  metadata.gz: 1af6e37035c37c270036487e9b939f40e8454d39ddea9983a737f409957e0747
+  data.tar.gz: 95438909311aa595d2d4e771424765f3705cdc649225ca81c053e3b9c129b183
 SHA512:
-  metadata.gz: 60777fcaababf8cc08559a582380fba24fa5a506a4751a0bb63e2a46957723dd4cbaf8c232ccb0ccfa91694c9723c24c054e708e27f59476c4734b58e1cd8269
-  data.tar.gz: f0f19ab3392f2d7a8f463b6c74b6e204024701502a86640bbfa3a207554ff69a25f53e36075aa14f65561f3187e2c24b0ae1db2f6ec7ac0630e3c83232a12ce4
+  metadata.gz: d2a9f542cfaaf8bb9e84ebf976694c548e153e1e170417309644b9206bf4df2ba8844447cbb2b0afd4ba8d03922688f6348a6fb77a6c8489a3f2a49bb873fed9
+  data.tar.gz: 514fab3aa32f39e1ebe6e4bf164a9b9f648b82e7aa861d9cbc2edd6d44d9c6b4d9d3ea9b7c281ae26bf719e4373bde6059f220033dc660821a369b6186180798

data/CHANGELOG.md

@@ -1,5 +1,27 @@
 # Beta
 
+## 0.1.14.beta
+- Add configurable max retries for requests when running into errors.
+- Add ability to send messages to the dead letter queue if we exhaust all retries and if it is configured.
+- Log truncated error body for all errors to help with debugging.
+
+## 0.1.13
+- Fix synchronization of status message sending code to avoid duplicate logs.
+
+## 0.1.12
+- Add logging of successful request retries after an error for additional clarity.
+- Add debug level logging of request body on error.
+
+## 0.1.11.beta
+- Fixes to retry mechanisms.
+- More thorough catching of events, preferring to retry requests rather than crashing the plugin.
+
+## 0.1.10.beta
+
+- Switch to shared concurrency to allow the use of multiple worker threads for increased
+  throughput.
+- Switch HTTP client library to `manticore` to work better with new shared concurrency.
+
 ## 0.1.9
 
 - Add support for logging status messages with metrics to stdout in addition to sending this

data/Gemfile

@@ -10,6 +10,11 @@ if Dir.exist?(logstash_path) && use_logstash_source
   gem 'logstash-core-plugin-api', :path => "#{logstash_path}/logstash-core-plugin-api"
 end
 
+group :test do
+  gem "webmock"
+end
+
 gem 'pry'
 gem 'pry-nav'
 gem 'quantile'
+gem 'manticore', platform: :jruby

data/README.md

@@ -10,7 +10,7 @@ You can view documentation for this plugin [on the Scalyr website](https://app.s
 # Quick start
 
 1. Build the gem, run `gem build logstash-output-scalyr.gemspec` 
-2. Install the gem into a Logstash installation, run `/usr/share/logstash/bin/logstash-plugin install logstash-output-scalyr-0.1.9.gem` or follow the latest official instructions on working with plugins from Logstash.
+2. Install the gem into a Logstash installation, run `/usr/share/logstash/bin/logstash-plugin install logstash-output-scalyr-0.1.14.beta.gem` or follow the latest official instructions on working with plugins from Logstash.
 3. Configure the output plugin (e.g. add it to a pipeline .conf)
 4. Restart Logstash 
 
@@ -369,7 +369,7 @@ If you want to change status reporting interval you can do that by changing the
 ## Updating version
 
 Currently references to the version need to be manually updated, files to look in for this are `logstash-putput-scalyr.gemspec`,
- `client.rb`, twice in the CircleCI `Dockerfile`, and under "Quick Start" in this `README.md`.
+ `lib/scalyr/constants.rb`, and under "Quick Start" in this `README.md`.
 
 The changelog should also be updated with the latest version and changes of note.
 

data/lib/logstash/outputs/scalyr.rb

@@ -8,9 +8,7 @@ require "thread" # for safe queueing
 require "uri" # for escaping user input
 require 'json' # for converting event object to JSON for upload
 
-require 'net/http'
-require 'net/http/persistent'
-require 'net/https'
+require 'manticore'
 require 'rbzip2'
 require 'zlib'
 require 'stringio'
@@ -18,6 +16,7 @@ require 'quantile'
 
 require 'scalyr/common/client'
 require "scalyr/common/util"
+require "scalyr/constants"
 
 
 #---------------------------------------------------------------------------------------------------------------------
@@ -27,9 +26,7 @@ class LogStash::Outputs::Scalyr < LogStash::Outputs::Base
 
   config_name "scalyr"
 
-  # For correctness reasons we need to limit this plugin to a single worker, a single worker will be single concurrency
-  # anyway but we should be explicit.
-  concurrency :single
+  concurrency :shared
 
   # The Scalyr API write token, these are available at https://www.scalyr.com/keys.  This is the only compulsory configuration field required for proper upload
   config :api_write_token, :validate => :string, :required => true
@@ -37,12 +34,6 @@ class LogStash::Outputs::Scalyr < LogStash::Outputs::Base
   # If you have an EU-based Scalyr account, please use https://eu.scalyr.com/
   config :scalyr_server, :validate => :string, :default => "https://agent.scalyr.com/"
 
-  # Path to SSL bundle file.
-  config :ssl_ca_bundle_path, :validate => :string, :default => "/etc/ssl/certs/ca-bundle.crt"
-
-  # If we should append our built-in Scalyr cert to the one we find at `ssl_ca_bundle_path`.
-  config :append_builtin_cert, :validate => :boolean, :default => true
-
   # server_attributes is a dictionary of key value pairs that represents/identifies the logstash aggregator server
   # (where this plugin is running).  Keys are arbitrary except for the 'serverHost' key which holds special meaning to
   # Scalyr and is given special treatment in the Scalyr UI.  All of these attributes are optional (not required for logs
@@ -87,13 +78,22 @@ class LogStash::Outputs::Scalyr < LogStash::Outputs::Base
 
   # Initial interval in seconds between bulk retries. Doubled on each retry up to `retry_max_interval`
   config :retry_initial_interval, :validate => :number, :default => 1
+  # How many times to retry sending an event before giving up on it
+  config :max_retries, :validate => :number, :default => 5
+  # Whether or not to send messages that failed to send a max_retries amount of times to the DLQ or just drop them
+  config :send_to_dlq, :validate => :boolean, :default => true
 
   # Set max interval in seconds between bulk retries.
   config :retry_max_interval, :validate => :number, :default => 64
 
-  # The following two settings pertain to preventing Man-in-the-middle (MITM) attacks  # echee TODO: eliminate?
+  # Whether or not to verify the connection to Scalyr, only set to false for debugging.
   config :ssl_verify_peer, :validate => :boolean, :default => true
-  config :ssl_verify_depth, :validate => :number, :default => 5
+
+  # Path to SSL bundle file.
+  config :ssl_ca_bundle_path, :validate => :string, :default => "/etc/ssl/certs/ca-bundle.crt"
+
+  # If we should append our built-in Scalyr cert to the one we find at `ssl_ca_bundle_path`.
+  config :append_builtin_cert, :validate => :boolean, :default => true
 
   config :max_request_buffer, :validate => :number, :default => 5500000  # echee TODO: eliminate?
   config :force_message_encoding, :validate => :string, :default => nil
@@ -132,6 +132,24 @@ class LogStash::Outputs::Scalyr < LogStash::Outputs::Base
   # Whether or not to create fresh quantile estimators after a status send. Depending on what you want to gather from
   # these stas this might be wanted or not.
   config :flush_quantile_estimates_on_status_send, :validate => :boolean, :default => false
+  
+  # Causes this plugin to act as if it successfully uploaded the logs, while actually returning as quickly as possible
+  # after no work being done.
+  config :noop_mode, :validate => :boolean, :default => false
+
+  # Manticore related options
+  config :http_connect_timeout, :validate => :number, :default => 10
+  config :http_socket_timeout, :validate => :number, :default => 10
+  config :http_request_timeout, :validate => :number, :default => 60
+  config :http_pool_max, :validate => :number, :default => 50
+  config :http_pool_max_per_route, :validate => :number, :default => 25
+
+  def initialize(*params)
+    super
+    # Request statistics are accumulated across multiple threads and must be accessed through a mutex
+    @stats_lock = Mutex.new
+    @send_stats = Mutex.new
+  end
 
   def close
     @running = false
@@ -140,6 +158,8 @@ class LogStash::Outputs::Scalyr < LogStash::Outputs::Base
 
   public
   def register
+    # This prng is used exclusively to determine when to sample statistics and no security related purpose, for this
+    # reason we do not ensure thread safety for it.
     @prng = Random.new
 
     if @event_metrics_sample_rate < 0 or @event_metrics_sample_rate > 1
@@ -223,12 +243,12 @@ class LogStash::Outputs::Scalyr < LogStash::Outputs::Base
     @running = true
     @client_session = Scalyr::Common::Client::ClientSession.new(
         @logger, @add_events_uri,
-        @compression_type, @compression_level,
-        @ssl_verify_peer, @ssl_ca_bundle_path, @ssl_verify_depth,
-        @append_builtin_cert, @record_stats_for_status, @flush_quantile_estimates_on_status_send
+        @compression_type, @compression_level, @ssl_verify_peer, @ssl_ca_bundle_path, @append_builtin_cert,
+        @record_stats_for_status, @flush_quantile_estimates_on_status_send,
+        @http_connect_timeout, @http_socket_timeout, @http_request_timeout, @http_pool_max, @http_pool_max_per_route
     )
 
-    @logger.info("Started Scalyr output plugin", :class => self.class.name)
+    @logger.info(sprintf("Started Scalyr output plugin (%s)." % [PLUGIN_VERSION]), :class => self.class.name)
 
     # Finally, send a status line to Scalyr
     send_status
@@ -241,7 +261,8 @@ class LogStash::Outputs::Scalyr < LogStash::Outputs::Base
       :multi_receive_duration_secs => Quantile::Estimator.new,
       :multi_receive_event_count => Quantile::Estimator.new,
       :event_attributes_count => Quantile::Estimator.new,
-      :flatten_values_duration_secs => Quantile::Estimator.new
+      :flatten_values_duration_secs => Quantile::Estimator.new,
+      :batches_per_multi_receive => Quantile::Estimator.new
     }
   end
 
@@ -257,87 +278,154 @@ class LogStash::Outputs::Scalyr < LogStash::Outputs::Base
   #
   public
   def multi_receive(events)
-    start_time = Time.now.to_f
+    # Just return and pretend we did something if running in noop mode
+    return events if @noop_mode
 
-    multi_event_request_array = build_multi_event_request_array(events)
-    # Loop over all array of multi-event requests, sending each multi-event to Scalyr
+    begin
+      start_time = Time.now.to_f
 
-    sleep_interval = @retry_initial_interval
-    batch_num = 1
-    total_batches = multi_event_request_array.length unless multi_event_request_array.nil?
+      multi_event_request_array = build_multi_event_request_array(events)
+      # Loop over all array of multi-event requests, sending each multi-event to Scalyr
 
-    result = []
-    records_count = events.to_a.length
+      sleep_interval = @retry_initial_interval
+      batch_num = 1
+      total_batches = multi_event_request_array.length unless multi_event_request_array.nil?
 
-    while !multi_event_request_array.to_a.empty?
-      begin
+      result = []
+      records_count = events.to_a.length
+
+      while !multi_event_request_array.to_a.empty?
         multi_event_request = multi_event_request_array.pop
-        # For some reason a retry on the multi_receive may result in the request array containing `nil` elements, we
-        # ignore these.
-        if !multi_event_request.nil?
-          @client_session.post_add_events(multi_event_request[:body], false, multi_event_request[:serialization_duration])
-          sleep_interval = 0
-          result.push(multi_event_request)
+        # Variables to hold information about exceptions we run into, and our handling of retries for this request. We
+        # track this to log it when the retries succeed so we can be sure logs are going through.
+        # General exception info we log in the error
+        exc_data = nil
+        # Whether the exception is commonly retried or not, for determining log level
+        exc_commonly_retried = false
+        # Count of retries attempted for this request
+        exc_retries = 0
+        # Total time spent sleeping while retrying this request due to backoff
+        exc_sleep = 0
+        begin
+          # For some reason a retry on the multi_receive may result in the request array containing `nil` elements, we
+          # ignore these.
+          if !multi_event_request.nil?
+            @client_session.post_add_events(multi_event_request[:body], false, multi_event_request[:serialization_duration])
+
+            sleep_interval = @retry_initial_interval
+            batch_num += 1
+            result.push(multi_event_request)
+          end
+
+        rescue Scalyr::Common::Client::ServerError, Scalyr::Common::Client::ClientError => e
+          sleep_interval = sleep_for(sleep_interval)
+          exc_sleep += sleep_interval
+          exc_retries += 1
+          message = "Error uploading to Scalyr (will backoff-retry)"
+          exc_data = {
+              :error_class => e.e_class,
+              :url => e.url.to_s,
+              :message => e.message,
+              :batch_num => batch_num,
+              :total_batches => total_batches,
+              :record_count => multi_event_request[:record_count],
+              :payload_size => multi_event_request[:body].bytesize,
+              :will_retry_in_seconds => sleep_interval,
+          }
+          exc_data[:code] = e.code if e.code
+          if @logger.debug? and e.body
+            exc_data[:body] = e.body
+          elsif e.body
+            exc_data[:body] = Scalyr::Common::Util.truncate(e.body, 512)
+          end
+          exc_data[:payload] = "\tSample payload: #{request[:body][0,1024]}..." if @logger.debug?
+          if e.is_commonly_retried?
+            # well-known retriable errors should be debug
+            @logger.debug(message, exc_data)
+            exc_commonly_retried = true
+          else
+            # all other failed uploads should be errors
+            @logger.error(message, exc_data)
+            exc_commonly_retried = false
+          end
+          retry if @running and exc_retries < @max_retries
+          log_retry_failure(multi_event_request, exc_data, exc_retries, exc_sleep)
+          next
+
+        rescue => e
+          # Any unexpected errors should be fully logged
+          @logger.error(
+              "Unexpected error occurred while uploading to Scalyr (will backoff-retry)",
+              :error_message => e.message,
+              :error_class => e.class.name,
+              :backtrace => e.backtrace
+          )
+          @logger.debug("Failed multi_event_request", :multi_event_request => multi_event_request)
+          sleep_interval = sleep_for(sleep_interval)
+          exc_data = {
+            :error_message => e.message,
+            :error_class => e.class.name,
+            :backtrace => e.backtrace,
+            :multi_event_request => multi_event_request
+          }
+          exc_sleep += sleep_interval
+          exc_retries += 1
+          retry if @running and exc_retries < @max_retries
+          log_retry_failure(multi_event_request, exc_data, exc_retries, exc_sleep)
+          next
         end
 
-      rescue OpenSSL::SSL::SSLError => e
-        # cannot rely on exception message, so we always log the following warning
-        @logger.error "SSL certificate verification failed.  " +
-        "Please make sure your certificate bundle is configured correctly and points to a valid file.  " +
-        "You can configure this with the ssl_ca_bundle_path configuration option.  " +
-        "The current value of ssl_ca_bundle_path is '#{@ssl_ca_bundle_path}'"
-        @logger.error e.message
-        @logger.error "Discarding buffer chunk without retrying."
-
-      rescue Scalyr::Common::Client::ServerError, Scalyr::Common::Client::ClientError => e
-        sleep_interval = sleep_for(sleep_interval)
-        message = "Error uploading to Scalyr (will backoff-retry)"
-        exc_data = {
-            :url => e.url.to_s,
-            :message => e.message,
-            :batch_num => batch_num,
-            :total_batches => total_batches,
-            :record_count => multi_event_request[:record_count],
-            :payload_size => multi_event_request[:body].bytesize,
-            :will_retry_in_seconds => sleep_interval,
-        }
-        exc_data[:code] = e.response_code if e.code
-        exc_data[:body] = e.response_body if @logger.debug? and e.body
-        exc_data[:payload] = "\tSample payload: #{request[:body][0,1024]}..." if @logger.debug?
-        if e.is_commonly_retried?
-          # well-known retriable errors should be debug
-          @logger.debug(message, exc_data)
-        else
-          # all other failed uploads should be errors
-          @logger.error(message, exc_data)
+        if !exc_data.nil?
+          message = "Retry successful after error."
+          if exc_commonly_retried
+            @logger.debug(message, :error_data => exc_data, :retries => exc_retries, :sleep_time => exc_sleep)
+          else
+            @logger.info(message, :error_data => exc_data, :retries => exc_retries, :sleep_time => exc_sleep)
+          end
         end
-        retry if @running
+      end
 
-      rescue => e
-        # Any unexpected errors should be fully logged
-        @logger.error(
-            "Unexpected error occurred while uploading to Scalyr (will backoff-retry)",
-            :error_message => e.message,
-            :error_class => e.class.name,
-            :backtrace => e.backtrace
-        )
-        @logger.debug("Failed multi_event_request", :multi_event_request => multi_event_request)
-        sleep_interval = sleep_for(sleep_interval)
-        retry if @running
+      if records_count > 0
+        @stats_lock.synchronize do
+          @multi_receive_statistics[:total_multi_receive_secs] += (Time.now.to_f - start_time)
+          @plugin_metrics[:multi_receive_duration_secs].observe(Time.now.to_f - start_time)
+          @plugin_metrics[:multi_receive_event_count].observe(records_count)
+          @plugin_metrics[:batches_per_multi_receive].observe(total_batches)
+        end
       end
-    end
 
-    if records_count > 0
-      @multi_receive_statistics[:total_multi_receive_secs] += (Time.now.to_f - start_time)
-      @plugin_metrics[:multi_receive_duration_secs].observe(Time.now.to_f - start_time)
-      @plugin_metrics[:multi_receive_event_count].observe(records_count)
+      send_status
+      return result
+
+    rescue => e
+      # Any unexpected errors should be fully logged
+      @logger.error(
+          "Unexpected error occurred while executing multi_receive.",
+          :error_message => e.message,
+          :error_class => e.class.name,
+          :backtrace => e.backtrace
+      )
     end
-
-    send_status
-    return result
   end  # def multi_receive
 
 
+  def log_retry_failure(multi_event_request, exc_data, exc_retries, exc_sleep)
+    message = "Failed to send #{multi_event_request[:logstash_events].length} events after #{exc_retries} tries."
+    sample_events = Array.new
+    multi_event_request[:logstash_events][0,5].each {|l_event|
+      sample_events << Scalyr::Common::Util.truncate(l_event.to_hash.to_json, 256)
+    }
+    @logger.error(message, :error_data => exc_data, :sample_events => sample_events, :retries => exc_retries, :sleep_time => exc_sleep)
+    if @dlq_writer
+      multi_event_request[:logstash_events].each {|l_event|
+        @dlq_writer.write(l_event, "#{exc_data[:message]}")
+      }
+    else
+      @logger.warn("Deal letter queue not configured, dropping #{multi_event_request[:logstash_events].length} events after #{exc_retries} tries.", :sample_events => sample_events)
+    end
+  end
+
+
   # Builds an array of multi-event requests from LogStash events
   # Each array element is a request that groups multiple events (to be posted to Scalyr's addEvents endpoint)
   #
@@ -366,6 +454,8 @@ class LogStash::Outputs::Scalyr < LogStash::Outputs::Base
     current_threads = Hash.new
     # Create a Scalyr event object for each record in the chunk
     scalyr_events = Array.new
+    # Track the logstash events in each chunk to send them to the dlq in case of an error
+    l_events = Array.new
 
     thread_ids = Hash.new
     next_id = 1 #incrementing thread id for the session
@@ -501,10 +591,12 @@ class LogStash::Outputs::Scalyr < LogStash::Outputs::Base
       end
 
       if should_sample_event_metrics
-        @plugin_metrics[:event_attributes_count].observe(record.count)
+        @stats_lock.synchronize do
+          @plugin_metrics[:event_attributes_count].observe(record.count)
 
-        if @flatten_nested_values
-          @plugin_metrics[:flatten_values_duration_secs].observe(flatten_nested_values_duration)
+          if @flatten_nested_values
+            @plugin_metrics[:flatten_values_duration_secs].observe(flatten_nested_values_duration)
+          end
         end
       end
 
@@ -555,9 +647,10 @@ class LogStash::Outputs::Scalyr < LogStash::Outputs::Base
         # make sure we always have at least one event
         if scalyr_events.size == 0
           scalyr_events << scalyr_event
+          l_events << l_event
           append_event = false
         end
-        multi_event_request = self.create_multi_event_request(scalyr_events, current_threads, logs)
+        multi_event_request = self.create_multi_event_request(scalyr_events, l_events, current_threads, logs)
         multi_event_request_array << multi_event_request
 
         total_bytes = 0
@@ -565,19 +658,21 @@ class LogStash::Outputs::Scalyr < LogStash::Outputs::Base
         logs = Hash.new
         logs_ids = Hash.new
         scalyr_events = Array.new
+        l_events = Array.new
       end
 
       # if we haven't consumed the current event already
       # add it to the end of our array and keep track of the json bytesize
       if append_event
         scalyr_events << scalyr_event
+        l_events << l_event
         total_bytes += add_bytes
       end
 
     }
 
     # create a final request with any left over events
-    multi_event_request = self.create_multi_event_request(scalyr_events, current_threads, logs)
+    multi_event_request = self.create_multi_event_request(scalyr_events, l_events, current_threads, logs)
     multi_event_request_array << multi_event_request
     multi_event_request_array
   end
@@ -595,10 +690,10 @@ class LogStash::Outputs::Scalyr < LogStash::Outputs::Base
   # A request comprises multiple Scalyr Events.  This function creates a request hash for
   # final upload to Scalyr (from an array of events, and an optional hash of current threads)
   # Note: The request body field will be json-encoded.
-  def create_multi_event_request(scalyr_events, current_threads, current_logs)
+  def create_multi_event_request(scalyr_events, logstash_events, current_threads, current_logs)
 
     body = {
-      :session => @session_id,
+      :session => @session_id + Thread.current.object_id.to_s,
       :token => @api_write_token,
       :events => scalyr_events,
     }
@@ -631,40 +726,49 @@ class LogStash::Outputs::Scalyr < LogStash::Outputs::Base
     serialized_body = body.to_json
     end_time = Time.now.to_f
     serialization_duration = end_time - start_time
-    { :body => serialized_body, :record_count => scalyr_events.size, :serialization_duration => serialization_duration }
+    {
+      :body => serialized_body, :record_count => scalyr_events.size, :serialization_duration => serialization_duration,
+      :logstash_events => logstash_events
+    }
 
   end  # def create_multi_event_request
 
 
   # Retrieve batch and other event level metric values
   def get_stats
-    current_stats = @multi_receive_statistics.clone
+    @stats_lock.synchronize do
+      current_stats = @multi_receive_statistics.clone
 
-    current_stats[:multi_receive_duration_p50] = @plugin_metrics[:multi_receive_duration_secs].query(0.5)
-    current_stats[:multi_receive_duration_p90] = @plugin_metrics[:multi_receive_duration_secs].query(0.9)
-    current_stats[:multi_receive_duration_p99] = @plugin_metrics[:multi_receive_duration_secs].query(0.99)
+      current_stats[:multi_receive_duration_p50] = @plugin_metrics[:multi_receive_duration_secs].query(0.5)
+      current_stats[:multi_receive_duration_p90] = @plugin_metrics[:multi_receive_duration_secs].query(0.9)
+      current_stats[:multi_receive_duration_p99] = @plugin_metrics[:multi_receive_duration_secs].query(0.99)
 
-    current_stats[:multi_receive_event_count_p50] = @plugin_metrics[:multi_receive_event_count].query(0.5)
-    current_stats[:multi_receive_event_count_p90] = @plugin_metrics[:multi_receive_event_count].query(0.9)
-    current_stats[:multi_receive_event_count_p99] = @plugin_metrics[:multi_receive_event_count].query(0.99)
+      current_stats[:multi_receive_event_count_p50] = @plugin_metrics[:multi_receive_event_count].query(0.5)
+      current_stats[:multi_receive_event_count_p90] = @plugin_metrics[:multi_receive_event_count].query(0.9)
+      current_stats[:multi_receive_event_count_p99] = @plugin_metrics[:multi_receive_event_count].query(0.99)
 
-    current_stats[:event_attributes_count_p50] = @plugin_metrics[:event_attributes_count].query(0.5)
-    current_stats[:event_attributes_count_p90] = @plugin_metrics[:event_attributes_count].query(0.9)
-    current_stats[:event_attributes_count_p99] = @plugin_metrics[:event_attributes_count].query(0.99)
+      current_stats[:event_attributes_count_p50] = @plugin_metrics[:event_attributes_count].query(0.5)
+      current_stats[:event_attributes_count_p90] = @plugin_metrics[:event_attributes_count].query(0.9)
+      current_stats[:event_attributes_count_p99] = @plugin_metrics[:event_attributes_count].query(0.99)
 
-    if @flatten_nested_values
-      # We only return those metrics in case flattening is enabled
-      current_stats[:flatten_values_duration_secs_p50] = @plugin_metrics[:flatten_values_duration_secs].query(0.5)
-      current_stats[:flatten_values_duration_secs_p90] = @plugin_metrics[:flatten_values_duration_secs].query(0.9)
-      current_stats[:flatten_values_duration_secs_p99] = @plugin_metrics[:flatten_values_duration_secs].query(0.99)
-    end
+      current_stats[:batches_per_multi_receive_p50] = @plugin_metrics[:batches_per_multi_receive].query(0.5)
+      current_stats[:batches_per_multi_receive_p90] = @plugin_metrics[:batches_per_multi_receive].query(0.9)
+      current_stats[:batches_per_multi_receive_p99] = @plugin_metrics[:batches_per_multi_receive].query(0.99)
 
-    if @flush_quantile_estimates_on_status_send
-      @logger.debug "Recreating / reseting quantile estimator classes for plugin metrics"
-      @plugin_metrics = get_new_metrics
-    end
+      if @flatten_nested_values
+        # We only return those metrics in case flattening is enabled
+        current_stats[:flatten_values_duration_secs_p50] = @plugin_metrics[:flatten_values_duration_secs].query(0.5)
+        current_stats[:flatten_values_duration_secs_p90] = @plugin_metrics[:flatten_values_duration_secs].query(0.9)
+        current_stats[:flatten_values_duration_secs_p99] = @plugin_metrics[:flatten_values_duration_secs].query(0.99)
+      end
+
+      if @flush_quantile_estimates_on_status_send
+        @logger.debug "Recreating / reseting quantile estimator classes for plugin metrics"
+        @plugin_metrics = get_new_metrics
+      end
 
-    current_stats
+      current_stats
+    end
   end
 
 
@@ -683,37 +787,56 @@ class LogStash::Outputs::Scalyr < LogStash::Outputs::Base
         'plugin_id' => self.id,
       }
     }
-
-    if !@last_status_transmit_time
-      status_event[:attrs]['message'] = "Started Scalyr LogStash output plugin."
-      status_event[:attrs]['serverHost'] = @node_hostname
-    else
-      cur_time = Time.now()
-      return if (cur_time.to_i - @last_status_transmit_time.to_i) < @status_report_interval
-      # echee TODO: get instance stats from session and create a status log line
-      msg = 'plugin_status: '
-      cnt = 0
-      @client_session.get_stats.each do |k, v|
-        val = v.instance_of?(Float) ? sprintf("%.4f", v) : v
-        val = val.nil? ? 0 : val
-        msg << ' ' if cnt > 0
-        msg << "#{k.to_s}=#{val}"
-        cnt += 1
+    @send_stats.synchronize do
+      if !@last_status_transmit_time
+        status_event[:attrs]['message'] = sprintf("Started Scalyr LogStash output plugin (%s)." % [PLUGIN_VERSION])
+        status_event[:attrs]['serverHost'] = @node_hostname
+      else
+        cur_time = Time.now()
+        return if (cur_time.to_i - @last_status_transmit_time.to_i) < @status_report_interval
+        # echee TODO: get instance stats from session and create a status log line
+        msg = 'plugin_status: '
+        cnt = 0
+        @client_session.get_stats.each do |k, v|
+          val = v.instance_of?(Float) ? sprintf("%.4f", v) : v
+          val = val.nil? ? 0 : val
+          msg << ' ' if cnt > 0
+          msg << "#{k.to_s}=#{val}"
+          cnt += 1
+        end
+        get_stats.each do |k, v|
+          val = v.instance_of?(Float) ? sprintf("%.4f", v) : v
+          val = val.nil? ? 0 : val
+          msg << ' ' if cnt > 0
+          msg << "#{k.to_s}=#{val}"
+          cnt += 1
+        end
+        status_event[:attrs]['message'] = msg
+        status_event[:attrs]['serverHost'] = @node_hostname
+        status_event[:attrs]['parser'] = @status_parser
       end
-      get_stats.each do |k, v|
-        val = v.instance_of?(Float) ? sprintf("%.4f", v) : v
-        val = val.nil? ? 0 : val
-        msg << ' ' if cnt > 0
-        msg << "#{k.to_s}=#{val}"
-        cnt += 1
+      multi_event_request = create_multi_event_request([status_event], nil, nil, nil)
+      begin
+        @client_session.post_add_events(multi_event_request[:body], true, 0)
+      rescue => e
+        if e.body
+          @logger.warn(
+            "Unexpected error occurred while uploading status to Scalyr",
+            :error_message => e.message,
+            :error_class => e.class.name,
+            :body => Scalyr::Common::Util.truncate(e.body, 512)
+          )
+        else
+          @logger.warn(
+            "Unexpected error occurred while uploading status to Scalyr",
+            :error_message => e.message,
+            :error_class => e.class.name
+          )
+        end
+        return
       end
-      status_event[:attrs]['message'] = msg
-      status_event[:attrs]['serverHost'] = @node_hostname
-      status_event[:attrs]['parser'] = @status_parser
+      @last_status_transmit_time = Time.now()
     end
-    multi_event_request = create_multi_event_request([status_event], nil, nil)
-    @client_session.post_add_events(multi_event_request[:body], true, 0)
-    @last_status_transmit_time = Time.now()
 
     if @log_status_messages_to_stdout
       @logger.info msg