Class: Fluent::KafkaGroupInput

Inherits:
Input
  • Object
show all
Includes:
Fluent::KafkaPluginUtil::SSLSettings, Fluent::KafkaPluginUtil::SaslSettings
Defined in:
lib/fluent/plugin/in_kafka_group.rb

Defined Under Namespace

Classes: ForShutdown

Constant Summary collapse

BufferError = 
if defined?(Fluent::Plugin::Buffer::BufferOverflowError)
  Fluent::Plugin::Buffer::BufferOverflowError
else
  Fluent::BufferQueueLimitError
end

Constants included from Fluent::KafkaPluginUtil::SSLSettings

Fluent::KafkaPluginUtil::SSLSettings::DummyFormatter

Instance Method Summary collapse

Methods included from Fluent::KafkaPluginUtil::SaslSettings

included

Methods included from Fluent::KafkaPluginUtil::SSLSettings

included, #pickup_ssl_endpoint, #read_ssl_file

Constructor Details

#initialize ⇒ KafkaGroupInput

Returns a new instance of KafkaGroupInput.



89
90
91
92
93
94
95
 
# File 'lib/fluent/plugin/in_kafka_group.rb', line 89

def initialize
  super
  require 'kafka'

  @time_parser = nil
  @retry_count = 1
end

Instance Method Details

#configure(conf) ⇒ Object 



111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
 
# File 'lib/fluent/plugin/in_kafka_group.rb', line 111

def configure(conf)
  super

  $log.info "Will watch for topics #{@topics} at brokers " \
            "#{@brokers} and '#{@consumer_group}' group"

  @topics = _config_to_array(@topics)

  if conf['max_wait_ms']
    log.warn "'max_wait_ms' parameter is deprecated. Use second unit 'max_wait_time' instead"
    @max_wait_time = conf['max_wait_ms'].to_i / 1000
  end

  @parser_proc = setup_parser(conf)

  @consumer_opts = {:group_id => @consumer_group}
  @consumer_opts[:session_timeout] = @session_timeout if @session_timeout
  @consumer_opts[:offset_commit_interval] = @offset_commit_interval if @offset_commit_interval
  @consumer_opts[:offset_commit_threshold] = @offset_commit_threshold if @offset_commit_threshold
  @consumer_opts[:fetcher_max_queue_size] = @fetcher_max_queue_size if @fetcher_max_queue_size

  @fetch_opts = {}
  @fetch_opts[:max_wait_time] = @max_wait_time if @max_wait_time
  @fetch_opts[:min_bytes] = @min_bytes if @min_bytes

  @time_source = :record if @use_record_time

  if @time_source == :record and @time_format
    if defined?(Fluent::TimeParser)
      @time_parser = Fluent::TimeParser.new(@time_format)
    else
      @time_parser = Fluent::TextParser::TimeParser.new(@time_format)
    end
  end

  if @time_source == :record && defined?(Fluent::NumericTimeParser)
    @float_numeric_parse = Fluent::NumericTimeParser.new(:float)
  end
end

#emit_events(tag, es) ⇒ Object 



367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
 
# File 'lib/fluent/plugin/in_kafka_group.rb', line 367

def emit_events(tag, es)
  retries = 0
  begin
    router.emit_stream(tag, es)
  rescue BufferError
    raise ForShutdown if @consumer.nil?

    if @retry_emit_limit.nil?
      sleep 1
      retry
    end

    if retries < @retry_emit_limit
      retries += 1
      sleep 1
      retry
    else
      raise RuntimeError, "Exceeds retry_emit_limit"
    end
  end
end

#multi_workers_ready? ⇒ Boolean

Returns:

  • (Boolean) 


105
106
107
 
# File 'lib/fluent/plugin/in_kafka_group.rb', line 105

def multi_workers_ready?
  true
end

#process_batch(batch) ⇒ Object 



300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
 
# File 'lib/fluent/plugin/in_kafka_group.rb', line 300

def process_batch(batch)
  es = Fluent::MultiEventStream.new
  tag = batch.topic
  tag = @add_prefix + "." + tag if @add_prefix
  tag = tag + "." + @add_suffix if @add_suffix

  batch.messages.each { |msg|
    begin
      record = @parser_proc.call(msg)
      case @time_source
      when :kafka
        record_time = Fluent::EventTime.from_time(msg.create_time)
      when :now
        record_time = Fluent::Engine.now
      when :record
        record_time = record[@record_time_key]

        if @time_format
          record_time = @time_parser.parse(record_time.to_s)
        elsif record_time.is_a?(Float) && @float_numeric_parse
          record_time = @float_numeric_parse.parse(record_time)
        end
      else
        log.fatal "BUG: invalid time_source: #{@time_source}"
      end
      if @kafka_message_key
        record[@kafka_message_key] = msg.key
      end
      if @add_headers
        msg.headers.each_pair { |k, v|
          record[k] = v
        }
      end
      es.add(record_time, record)
    rescue => e
      log.warn "parser error in #{batch.topic}/#{batch.partition}", :error => e.to_s, :value => msg.value, :offset => msg.offset
      log.debug_backtrace
    end
  }

  unless es.empty?
    emit_events(tag, es)
  end
end

#process_batch_with_record_tag(batch) ⇒ Object 



255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
 
# File 'lib/fluent/plugin/in_kafka_group.rb', line 255

def process_batch_with_record_tag(batch)
  es = {} 
  batch.messages.each { |msg|
    begin
      record = @parser_proc.call(msg)
      tag = record[@record_tag_key]
      tag = @add_prefix + "." + tag if @add_prefix
      tag = tag + "." + @add_suffix if @add_suffix
      es[tag] ||= Fluent::MultiEventStream.new
      case @time_source
      when :kafka
        record_time = Fluent::EventTime.from_time(msg.create_time)
      when :now
        record_time = Fluent::Engine.now
      when :record
        if @time_format
          record_time = @time_parser.parse(record[@record_time_key].to_s)
        else
          record_time = record[@record_time_key]
        end
      else
        log.fatal "BUG: invalid time_source: #{@time_source}"
      end
      if @kafka_message_key
        record[@kafka_message_key] = msg.key
      end
      if @add_headers
        msg.headers.each_pair { |k, v|
          record[k] = v
        }
      end
      es[tag].add(record_time, record)
    rescue => e
      log.warn "parser error in #{batch.topic}/#{batch.partition}", :error => e.to_s, :value => msg.value, :offset => msg.offset
      log.debug_backtrace
    end
  }

  unless es.empty?
    es.each { |tag,es|
      emit_events(tag, es)
    }
  end
end

#reconnect_consumer ⇒ Object 



234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
 
# File 'lib/fluent/plugin/in_kafka_group.rb', line 234

def reconnect_consumer
  log.warn "Stopping Consumer"
  consumer = @consumer
  @consumer = nil
  if consumer
    consumer.stop
  end
  log.warn "Could not connect to broker. retry_time:#{@retry_count}. Next retry will be in #{@retry_wait_seconds} seconds"
  @retry_count = @retry_count + 1
  sleep @retry_wait_seconds
  @consumer = setup_consumer
  log.warn "Re-starting consumer #{Time.now.to_s}"
  @retry_count = 0
rescue =>e
  log.error "unexpected error during re-starting consumer object access", :error => e.to_s
  log.error_backtrace
  if @retry_count <= @retry_limit or disable_retry_limit
    reconnect_consumer
  end
end

#run ⇒ Object 



345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
 
# File 'lib/fluent/plugin/in_kafka_group.rb', line 345

def run
  while @consumer
    begin
      @consumer.each_batch(**@fetch_opts) { |batch|
        if @tag_source == :record
          process_batch_with_record_tag(batch)
        else
          process_batch(batch) 
        end
      }
    rescue ForShutdown
    rescue => e
      log.error "unexpected error during consuming events from kafka. Re-fetch events.", :error => e.to_s
      log.error_backtrace
      reconnect_consumer
    end
  end
rescue => e
  log.error "unexpected error during consumer object access", :error => e.to_s
  log.error_backtrace
end

#setup_consumer ⇒ Object 



219
220
221
222
223
224
225
226
227
228
229
230
231
232
 
# File 'lib/fluent/plugin/in_kafka_group.rb', line 219

def setup_consumer
  consumer = @kafka.consumer(**@consumer_opts)
  @topics.each { |topic|
    if m = /^\/(.+)\/$/.match(topic)
      topic_or_regex = Regexp.new(m[1])
      $log.info "Subscribe to topics matching the regex #{topic}"
    else
      topic_or_regex = topic
      $log.info "Subscribe to topic #{topic}"
    end
    consumer.subscribe(topic_or_regex, start_from_beginning: @start_from_beginning, max_bytes_per_partition: @max_bytes)
  }
  consumer
end

#setup_parser(conf) ⇒ Object 



151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
 
# File 'lib/fluent/plugin/in_kafka_group.rb', line 151

def setup_parser(conf)
  case @format
  when 'json'
    begin
      require 'oj'
      Oj.default_options = Fluent::DEFAULT_OJ_OPTIONS
      Proc.new { |msg| Oj.load(msg.value) }
    rescue LoadError
      require 'yajl'
      Proc.new { |msg| Yajl::Parser.parse(msg.value) }
    end
  when 'ltsv'
    require 'ltsv'
    Proc.new { |msg| LTSV.parse(msg.value, {:symbolize_keys => false}).first }
  when 'msgpack'
    require 'msgpack'
    Proc.new { |msg| MessagePack.unpack(msg.value) }
  when 'text'
    Proc.new { |msg| {@message_key => msg.value} }
  else
    @custom_parser = Fluent::Plugin.new_parser(conf['format'])
    @custom_parser.configure(conf)
    Proc.new { |msg|
      @custom_parser.parse(msg.value) {|_time, record|
        record
      }
    }
  end
end

#shutdown ⇒ Object 



206
207
208
209
210
211
212
213
214
215
216
217
 
# File 'lib/fluent/plugin/in_kafka_group.rb', line 206

def shutdown
  # This nil assignment should be guarded by mutex in multithread programming manner.
  # But the situation is very low contention, so we don't use mutex for now.
  # If the problem happens, we will add a guard for consumer.
  consumer = @consumer
  @consumer = nil
  consumer.stop

  @thread.join
  @kafka.close
  super
end

#start ⇒ Object 



181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
 
# File 'lib/fluent/plugin/in_kafka_group.rb', line 181

def start
  super

  logger = @get_kafka_client_log ? log : nil
  if @scram_mechanism != nil && @username != nil && @password != nil
    @kafka = Kafka.new(seed_brokers: @brokers, client_id: @client_id, logger: logger, connect_timeout: @connect_timeout, socket_timeout: @socket_timeout, ssl_ca_cert_file_path: @ssl_ca_cert,
                       ssl_client_cert: read_ssl_file(@ssl_client_cert), ssl_client_cert_key: read_ssl_file(@ssl_client_cert_key),
                       ssl_ca_certs_from_system: @ssl_ca_certs_from_system, sasl_scram_username: @username, sasl_scram_password: @password,
                       sasl_scram_mechanism: @scram_mechanism, sasl_over_ssl: @sasl_over_ssl, ssl_verify_hostname: @ssl_verify_hostname)
  elsif @username != nil && @password != nil
    @kafka = Kafka.new(seed_brokers: @brokers, client_id: @client_id, logger: logger, connect_timeout: @connect_timeout, socket_timeout: @socket_timeout, ssl_ca_cert_file_path: @ssl_ca_cert,
                       ssl_client_cert: read_ssl_file(@ssl_client_cert), ssl_client_cert_key: read_ssl_file(@ssl_client_cert_key),
                       ssl_ca_certs_from_system: @ssl_ca_certs_from_system, sasl_plain_username: @username, sasl_plain_password: @password,
                       sasl_over_ssl: @sasl_over_ssl, ssl_verify_hostname: @ssl_verify_hostname)
  else
    @kafka = Kafka.new(seed_brokers: @brokers, client_id: @client_id, logger: logger, connect_timeout: @connect_timeout, socket_timeout: @socket_timeout, ssl_ca_cert_file_path: @ssl_ca_cert,
                       ssl_client_cert: read_ssl_file(@ssl_client_cert), ssl_client_cert_key: read_ssl_file(@ssl_client_cert_key),
                       ssl_ca_certs_from_system: @ssl_ca_certs_from_system, sasl_gssapi_principal: @principal, sasl_gssapi_keytab: @keytab,
                       ssl_verify_hostname: @ssl_verify_hostname)
  end

  @consumer = setup_consumer
  @thread = Thread.new(&method(:run))
end