Class: Rdkafka::Consumer

Inherits:
Object
  • Object
show all
Includes:
Enumerable, Helpers::OAuth, Helpers::Time
Defined in:
lib/rdkafka/consumer.rb,
lib/rdkafka/consumer/headers.rb,
lib/rdkafka/consumer/message.rb,
lib/rdkafka/consumer/partition.rb,
lib/rdkafka/consumer/topic_partition_list.rb

Overview

A consumer of Kafka messages. It uses the high-level consumer approach where the Kafka brokers automatically assign partitions and load balance partitions over consumers that have the same :"group.id" set in their configuration.

To create a consumer set up a Config and call consumer on that. It is mandatory to set :"group.id" in the configuration.

Consumer implements Enumerable, so you can use each to consume messages, or for example each_slice to consume batches of messages.

Defined Under Namespace

Modules: Headers Classes: Message, Partition, TopicPartitionList

Instance Method Summary collapse

Methods included from Helpers::OAuth

#oauthbearer_set_token, #oauthbearer_set_token_failure

Methods included from Helpers::Time

#monotonic_now

Instance Method Details

#assign(list) ⇒ Object

Atomic assignment of partitions to consume

Parameters:

Raises:



181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
 
# File 'lib/rdkafka/consumer.rb', line 181

def assign(list)
  closed_consumer_check(__method__)

  unless list.is_a?(TopicPartitionList)
    raise TypeError.new("list has to be a TopicPartitionList")
  end

  tpl = list.to_native_tpl

  begin
    response = @native_kafka.with_inner do |inner|
      Rdkafka::Bindings.rd_kafka_assign(inner, tpl)
    end

    Rdkafka::RdkafkaError.validate!(response, "Error assigning '#{list.to_h}'")
  ensure
    Rdkafka::Bindings.rd_kafka_topic_partition_list_destroy(tpl)
  end
end

#assignment ⇒ TopicPartitionList

Returns the current partition assignment.

Returns:

Raises:



205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
 
# File 'lib/rdkafka/consumer.rb', line 205

def assignment
  closed_consumer_check(__method__)

  ptr = FFI::MemoryPointer.new(:pointer)
  response = @native_kafka.with_inner do |inner|
    Rdkafka::Bindings.rd_kafka_assignment(inner, ptr)
  end

  Rdkafka::RdkafkaError.validate!(response)

  tpl = ptr.read_pointer

  if !tpl.null?
    begin
      Rdkafka::Consumer::TopicPartitionList.from_native_tpl(tpl)
    ensure
      Rdkafka::Bindings.rd_kafka_topic_partition_list_destroy tpl
    end
  end
ensure
  ptr.free unless ptr.nil?
end

#assignment_lost? ⇒ Boolean

Returns true if our current assignment has been lost involuntarily.

Returns:

  • (Boolean) —

    true if our current assignment has been lost involuntarily.



229
230
231
232
233
234
235
 
# File 'lib/rdkafka/consumer.rb', line 229

def assignment_lost?
  closed_consumer_check(__method__)

  @native_kafka.with_inner do |inner|
    !Rdkafka::Bindings.rd_kafka_assignment_lost(inner).zero?
  end
end

#close ⇒ nil

Close this consumer

Returns:

  • (nil) 


42
43
44
45
46
47
48
49
50
51
 
# File 'lib/rdkafka/consumer.rb', line 42

def close
  return if closed?
  ObjectSpace.undefine_finalizer(self)

  @native_kafka.synchronize do |inner|
    Rdkafka::Bindings.rd_kafka_consumer_close(inner)
  end

  @native_kafka.close
end

#closed? ⇒ Boolean

Whether this consumer has closed

Returns:

  • (Boolean) 


54
55
56
 
# File 'lib/rdkafka/consumer.rb', line 54

def closed?
  @native_kafka.closed?
end

#cluster_id ⇒ String?

Returns the ClusterId as reported in broker metadata.

Returns:

  • (String, nil) 


362
363
364
365
366
367
 
# File 'lib/rdkafka/consumer.rb', line 362

def cluster_id
  closed_consumer_check(__method__)
  @native_kafka.with_inner do |inner|
    Rdkafka::Bindings.rd_kafka_clusterid(inner)
  end
end

#commit(list = nil, async = false) ⇒ nil

Manually commit the current offsets of this consumer.

To use this set enable.auto.committo false to disable automatic triggering of commits.

If enable.auto.offset.store is set to true the offset of the last consumed message for every partition is used. If set to false you can use #store_offset to indicate when a message has been fully processed.

Parameters:

  • list (TopicPartitionList, nil) (defaults to: nil) —

    The topic with partitions to commit

  • async (Boolean) (defaults to: false) —

    Whether to commit async or wait for the commit to finish

Returns:

  • (nil)

Raises:



521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
 
# File 'lib/rdkafka/consumer.rb', line 521

def commit(list=nil, async=false)
  closed_consumer_check(__method__)

  if !list.nil? && !list.is_a?(TopicPartitionList)
    raise TypeError.new("list has to be nil or a TopicPartitionList")
  end

  tpl = list ? list.to_native_tpl : nil

  begin
    response = @native_kafka.with_inner do |inner|
      Rdkafka::Bindings.rd_kafka_commit(inner, tpl, async)
    end

    Rdkafka::RdkafkaError.validate!(response)

    nil
  ensure
    Rdkafka::Bindings.rd_kafka_topic_partition_list_destroy(tpl) if tpl
  end
end

#committed(list = nil, timeout_ms = 2_000) ⇒ TopicPartitionList

Return the current committed offset per partition for this consumer group. The offset field of each requested partition will either be set to stored offset or to -1001 in case there was no stored offset for that partition.

Parameters:

  • list (TopicPartitionList, nil) (defaults to: nil) —

    The topic with partitions to get the offsets for or nil to use the current subscription.

  • timeout_ms (Integer) (defaults to: 2_000) —

    The timeout for fetching this information.

Returns:

Raises:

  • (RdkafkaError) —

    When getting the committed positions fails.



246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
 
# File 'lib/rdkafka/consumer.rb', line 246

def committed(list=nil, timeout_ms=2_000)
  closed_consumer_check(__method__)

  if list.nil?
    list = assignment
  elsif !list.is_a?(TopicPartitionList)
    raise TypeError.new("list has to be nil or a TopicPartitionList")
  end

  tpl = list.to_native_tpl

  begin
    response = @native_kafka.with_inner do |inner|
      Rdkafka::Bindings.rd_kafka_committed(inner, tpl, timeout_ms)
    end

    Rdkafka::RdkafkaError.validate!(response)

    TopicPartitionList.from_native_tpl(tpl)
  ensure
    Rdkafka::Bindings.rd_kafka_topic_partition_list_destroy(tpl)
  end
end

#each {|message| ... } ⇒ nil

Poll for new messages and yield for each received one. Iteration will end when the consumer is closed.

If enable.partition.eof is turned on in the config this will raise an error when an eof is reached, so you probably want to disable that when using this method of iteration.

Yield Parameters:

  • message (Message) —

    Received message

Returns:

  • (nil)

Raises:



607
608
609
610
611
612
613
614
615
616
617
618
619
620
 
# File 'lib/rdkafka/consumer.rb', line 607

def each
  loop do
    message = poll(250)
    if message
      yield(message)
    else
      if closed?
        break
      else
        next
      end
    end
  end
end

#each_batch(max_items: 100, bytes_threshold: Float::INFINITY, timeout_ms: 250, yield_on_error: false, &block) ⇒ Object

Deprecated. Please read the error message for more details.

Raises:

  • (NotImplementedError) 


623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
 
# File 'lib/rdkafka/consumer.rb', line 623

def each_batch(max_items: 100, bytes_threshold: Float::INFINITY, timeout_ms: 250, yield_on_error: false, &block)
  raise NotImplementedError, <<~ERROR
    `each_batch` has been removed due to data consistency concerns.

    This method was removed because it did not properly handle partition reassignments,
    which could lead to processing messages from partitions that were no longer owned
    by this consumer, resulting in duplicate message processing and data inconsistencies.

    Recommended alternatives:

    1. Implement your own batching logic using rebalance callbacks to properly handle
       partition revocations and ensure message processing correctness.

    2. Use a high-level batching library that supports proper partition reassignment
       handling out of the box (such as the Karafka framework).
  ERROR
end

#events_poll(timeout_ms = 0) ⇒ Object

Note:

This method technically should be called #poll and the current #poll should be called #consumer_poll though we keep the current naming convention to make it backward compatible.

Polls the main rdkafka queue (not the consumer one). Do NOT use it if consumer_poll_set was set to true.

Events will cause application-provided callbacks to be called.

Events (in the context of the consumer): - error callbacks - stats callbacks - any other callbacks supported by librdkafka that are not part of the consumer_poll, that would have a callback configured and activated.

This method needs to be called at regular intervals to serve any queued callbacks waiting to be called. When in use, does NOT replace #poll but needs to run complementary with it.

Parameters:

  • timeout_ms (Integer) (defaults to: 0) —

    poll timeout. If set to 0 will run async, when set to -1 will block until any events available.



592
593
594
595
596
 
# File 'lib/rdkafka/consumer.rb', line 592

def events_poll(timeout_ms = 0)
  @native_kafka.with_inner do |inner|
    Rdkafka::Bindings.rd_kafka_poll(inner, timeout_ms)
  end
end

#finalizer ⇒ Object 



36
37
38
 
# File 'lib/rdkafka/consumer.rb', line 36

def finalizer
  ->(_) { close }
end

#lag(topic_partition_list, watermark_timeout_ms = 1000) ⇒ Hash<String, Hash<Integer, Integer>>

Calculate the consumer lag per partition for the provided topic partition list. You can get a suitable list by calling #committed or #position (TODO). It is also possible to create one yourself, in this case you have to provide a list that already contains all the partitions you need the lag for.

Parameters:

  • topic_partition_list (TopicPartitionList) —

    The list to calculate lag for.

  • watermark_timeout_ms (Integer) (defaults to: 1000) —

    The timeout for each query watermark call.

Returns:

  • (Hash<String, Hash<Integer, Integer>>) —

    A hash containing all topics with the lag per partition

Raises:



338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
 
# File 'lib/rdkafka/consumer.rb', line 338

def lag(topic_partition_list, watermark_timeout_ms=1000)
  out = {}

  topic_partition_list.to_h.each do |topic, partitions|
    # Query high watermarks for this topic's partitions
    # and compare to the offset in the list.
    topic_out = {}
    partitions.each do |p|
      next if p.offset.nil?
      _, high = query_watermark_offsets(
        topic,
        p.partition,
        watermark_timeout_ms
      )
      topic_out[p.partition] = high - p.offset
    end
    out[topic] = topic_out
  end
  out
end

#member_id ⇒ String?

Returns this client’s broker-assigned group member id

This currently requires the high-level KafkaConsumer

Returns:

  • (String, nil) 


374
375
376
377
378
379
 
# File 'lib/rdkafka/consumer.rb', line 374

def member_id
  closed_consumer_check(__method__)
  @native_kafka.with_inner do |inner|
    Rdkafka::Bindings.rd_kafka_memberid(inner)
  end
end

#name ⇒ String

Returns consumer name.

Returns:

  • (String) —

    consumer name



30
31
32
33
34
 
# File 'lib/rdkafka/consumer.rb', line 30

def name
  @name ||= @native_kafka.with_inner do |inner|
    ::Rdkafka::Bindings.rd_kafka_name(inner)
  end
end

#offsets_for_times(list, timeout_ms = 1000) ⇒ TopicPartitionList

Lookup offset for the given partitions by timestamp.

Parameters:

Returns:

Raises:

  • (RdKafkaError) —

    When the OffsetForTimes lookup fails



484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
 
# File 'lib/rdkafka/consumer.rb', line 484

def offsets_for_times(list, timeout_ms = 1000)
  closed_consumer_check(__method__)

  if !list.is_a?(TopicPartitionList)
    raise TypeError.new("list has to be a TopicPartitionList")
  end

  tpl = list.to_native_tpl

  response = @native_kafka.with_inner do |inner|
    Rdkafka::Bindings.rd_kafka_offsets_for_times(
      inner,
      tpl,
      timeout_ms # timeout
    )
  end

  Rdkafka::RdkafkaError.validate!(response)

  TopicPartitionList.from_native_tpl(tpl)
ensure
  Rdkafka::Bindings.rd_kafka_topic_partition_list_destroy(tpl) if tpl
end

#pause(list) ⇒ nil

Pause producing or consumption for the provided list of partitions

Parameters:

Returns:

  • (nil)

Raises:



104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
 
# File 'lib/rdkafka/consumer.rb', line 104

def pause(list)
  closed_consumer_check(__method__)

  unless list.is_a?(TopicPartitionList)
    raise TypeError.new("list has to be a TopicPartitionList")
  end

  tpl = list.to_native_tpl

  begin
    response = @native_kafka.with_inner do |inner|
      Rdkafka::Bindings.rd_kafka_pause_partitions(inner, tpl)
    end

    if response != 0
      list = TopicPartitionList.from_native_tpl(tpl)
      raise Rdkafka::RdkafkaTopicPartitionListError.new(response, list, "Error pausing '#{list.to_h}'")
    end
  ensure
    Rdkafka::Bindings.rd_kafka_topic_partition_list_destroy(tpl)
  end
end

#poll(timeout_ms) ⇒ Message?

Poll for the next message on one of the subscribed topics

Parameters:

  • timeout_ms (Integer) —

    Timeout of this poll

Returns:

  • (Message, nil) —

    A message or nil if there was no new message within the timeout

Raises:



548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
 
# File 'lib/rdkafka/consumer.rb', line 548

def poll(timeout_ms)
  closed_consumer_check(__method__)

  message_ptr = @native_kafka.with_inner do |inner|
    Rdkafka::Bindings.rd_kafka_consumer_poll(inner, timeout_ms)
  end

  return nil if message_ptr.null?

  # Create struct wrapper
  native_message = Rdkafka::Bindings::Message.new(message_ptr)

  # Create a message to pass out
  return Rdkafka::Consumer::Message.new(native_message) if native_message[:err].zero?

  # Raise error if needed
  Rdkafka::RdkafkaError.validate!(native_message)
ensure
  # Clean up rdkafka message if there is one
  if message_ptr && !message_ptr.null?
    Rdkafka::Bindings.rd_kafka_message_destroy(message_ptr)
  end
end

#position(list = nil) ⇒ TopicPartitionList

Return the current positions (offsets) for topics and partitions. The offset field of each requested partition will be set to the offset of the last consumed message + 1, or nil in case there was no previous message.

Parameters:

  • list (TopicPartitionList, nil) (defaults to: nil) —

    The topic with partitions to get the offsets for or nil to use the current subscription.

Returns:

Raises:



278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
 
# File 'lib/rdkafka/consumer.rb', line 278

def position(list=nil)
  if list.nil?
    list = assignment
  elsif !list.is_a?(TopicPartitionList)
    raise TypeError.new("list has to be nil or a TopicPartitionList")
  end

  tpl = list.to_native_tpl

  response = @native_kafka.with_inner do |inner|
    Rdkafka::Bindings.rd_kafka_position(inner, tpl)
  end

  Rdkafka::RdkafkaError.validate!(response)

  TopicPartitionList.from_native_tpl(tpl)
end

#query_watermark_offsets(topic, partition, timeout_ms = 1000) ⇒ Integer

Query broker for low (oldest/beginning) and high (newest/end) offsets for a partition.

Parameters:

  • topic (String) —

    The topic to query

  • partition (Integer) —

    The partition to query

  • timeout_ms (Integer) (defaults to: 1000) —

    The timeout for querying the broker

Returns:

  • (Integer) —

    The low and high watermark

Raises:



303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
 
# File 'lib/rdkafka/consumer.rb', line 303

def query_watermark_offsets(topic, partition, timeout_ms=1000)
  closed_consumer_check(__method__)

  low = FFI::MemoryPointer.new(:int64, 1)
  high = FFI::MemoryPointer.new(:int64, 1)

  response = @native_kafka.with_inner do |inner|
    Rdkafka::Bindings.rd_kafka_query_watermark_offsets(
      inner,
      topic,
      partition,
      low,
      high,
      timeout_ms,
    )
  end

  Rdkafka::RdkafkaError.validate!(response, "Error querying watermark offsets for partition #{partition} of #{topic}")

  return low.read_array_of_int64(1).first, high.read_array_of_int64(1).first
ensure
  low.free   unless low.nil?
  high.free  unless high.nil?
end

#resume(list) ⇒ nil

Resumes producing consumption for the provided list of partitions

Parameters:

Returns:

  • (nil)

Raises:



132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
 
# File 'lib/rdkafka/consumer.rb', line 132

def resume(list)
  closed_consumer_check(__method__)

  unless list.is_a?(TopicPartitionList)
    raise TypeError.new("list has to be a TopicPartitionList")
  end

  tpl = list.to_native_tpl

  begin
    response = @native_kafka.with_inner do |inner|
      Rdkafka::Bindings.rd_kafka_resume_partitions(inner, tpl)
    end

    Rdkafka::RdkafkaError.validate!(response, "Error resume '#{list.to_h}'")

    nil
  ensure
    Rdkafka::Bindings.rd_kafka_topic_partition_list_destroy(tpl)
  end
end

#seek(message) ⇒ nil

Seek to a particular message. The next poll on the topic/partition will return the message at the given offset.

Parameters:

Returns:

  • (nil)

Raises:



437
438
439
 
# File 'lib/rdkafka/consumer.rb', line 437

def seek(message)
  seek_by(message.topic, message.partition, message.offset)
end

#seek_by(topic, partition, offset) ⇒ nil

Seek to a particular message by providing the topic, partition and offset. The next poll on the topic/partition will return the message at the given offset.

Parameters:

  • topic (String) —

    The topic in which to seek

  • partition (Integer) —

    The partition number to seek

  • offset (Integer) —

    The partition offset to seek

Returns:

  • (nil)

Raises:



450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
 
# File 'lib/rdkafka/consumer.rb', line 450

def seek_by(topic, partition, offset)
  closed_consumer_check(__method__)

  # rd_kafka_offset_store is one of the few calls that does not support
  # a string as the topic, so create a native topic for it.
  native_topic = @native_kafka.with_inner do |inner|
    Rdkafka::Bindings.rd_kafka_topic_new(
      inner,
      topic,
      nil
    )
  end
  response = Rdkafka::Bindings.rd_kafka_seek(
    native_topic,
    partition,
    offset,
    0 # timeout
  )
  Rdkafka::RdkafkaError.validate!(response)

  nil
ensure
  if native_topic && !native_topic.null?
    Rdkafka::Bindings.rd_kafka_topic_destroy(native_topic)
  end
end

#start ⇒ Object

Note:

Not needed to run unless explicit start was disabled

Starts the native Kafka polling thread and kicks off the init polling



25
26
27
 
# File 'lib/rdkafka/consumer.rb', line 25

def start
  @native_kafka.start
end

#store_offset(message, metadata = nil) ⇒ nil

Store offset of a message to be used in the next commit of this consumer

When using this enable.auto.offset.store should be set to false in the config.

Parameters:

  • message (Rdkafka::Consumer::Message) —

    The message which offset will be stored

  • metadata (String, nil) (defaults to: nil) —

    commit metadata string or nil if none

Returns:

  • (nil)

Raises:



389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
 
# File 'lib/rdkafka/consumer.rb', line 389

def store_offset(message, metadata = nil)
  closed_consumer_check(__method__)

  list = TopicPartitionList.new

  # For metadata aware commits we build the partition reference directly to save on
  # objects allocations
  if metadata
    list.add_topic_and_partitions_with_offsets(
      message.topic,
      [
        Consumer::Partition.new(
          message.partition,
          message.offset + 1,
          0,
          metadata
        )
      ]
    )
  else
    list.add_topic_and_partitions_with_offsets(
      message.topic,
      message.partition => message.offset + 1
    )
  end

  tpl = list.to_native_tpl

  response = @native_kafka.with_inner do |inner|
    Rdkafka::Bindings.rd_kafka_offsets_store(
      inner,
      tpl
    )
  end

  Rdkafka::RdkafkaError.validate!(response)

  nil
ensure
  Rdkafka::Bindings.rd_kafka_topic_partition_list_destroy(tpl) if tpl
end

#subscribe(*topics) ⇒ nil

Subscribes to one or more topics letting Kafka handle partition assignments.

Parameters:

  • topics (Array<String>) —

    One or more topic names

Returns:

  • (nil)

Raises:



63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
 
# File 'lib/rdkafka/consumer.rb', line 63

def subscribe(*topics)
  closed_consumer_check(__method__)

  # Create topic partition list with topics and no partition set
  tpl = Rdkafka::Bindings.rd_kafka_topic_partition_list_new(topics.length)

  topics.each do |topic|
    Rdkafka::Bindings.rd_kafka_topic_partition_list_add(tpl, topic, -1)
  end

  # Subscribe to topic partition list and check this was successful
  response = @native_kafka.with_inner do |inner|
    Rdkafka::Bindings.rd_kafka_subscribe(inner, tpl)
  end

  Rdkafka::RdkafkaError.validate!(response, "Error subscribing to '#{topics.join(', ')}'")
ensure
  Rdkafka::Bindings.rd_kafka_topic_partition_list_destroy(tpl) unless tpl.nil?
end

#subscription ⇒ TopicPartitionList

Returns the current subscription to topics and partitions

Returns:

Raises:



158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
 
# File 'lib/rdkafka/consumer.rb', line 158

def subscription
  closed_consumer_check(__method__)

  ptr = FFI::MemoryPointer.new(:pointer)
  response = @native_kafka.with_inner do |inner|
    Rdkafka::Bindings.rd_kafka_subscription(inner, ptr)
  end

  Rdkafka::RdkafkaError.validate!(response)

  native = ptr.read_pointer

  begin
    Rdkafka::Consumer::TopicPartitionList.from_native_tpl(native)
  ensure
    Rdkafka::Bindings.rd_kafka_topic_partition_list_destroy(native)
  end
end

#unsubscribe ⇒ nil

Unsubscribe from all subscribed topics.

Returns:

  • (nil)

Raises:



87
88
89
90
91
92
93
94
95
96
97
 
# File 'lib/rdkafka/consumer.rb', line 87

def unsubscribe
  closed_consumer_check(__method__)

  response = @native_kafka.with_inner do |inner|
    Rdkafka::Bindings.rd_kafka_unsubscribe(inner)
  end

  Rdkafka::RdkafkaError.validate!(response)

  nil
end