I am trying to come up with a configuration that would enforce producer quota setup based on an average byte rate of producer.
I did a test with a 3 node cluster. The topic however was created with 1 partition and 1 replication factor so that the producer_byte_rate can be measured only for 1 broker (the leader broker).
I set the producer_byte_rate to 20480 on client id test_producer_quota.
I used kafka-producer-perf-test to test out the throughput and throttle.
kafka-producer-perf-test --producer-props bootstrap.servers=SSL://kafka-broker1:6667 \
client.id=test_producer_quota \
--topic quota_test \
--producer.config /myfolder/client.properties \
--record.size 2048 --num-records 4000 --throughput -1
I expected the producer client to learn about the throttle and eventually smooth out the requests sent to the broker. Instead I noticed there is alternate throghput of 98 rec/sec and 21 recs/sec for a period of more than 30 seconds. During this time average latency slowly kept increseing and finally when it hits 120000 ms, I start to see Timeout exception as below
org.apache.kafka.common.errors.TimeoutException : Expiring 7 records for quota_test-0: 120000 ms has passed since batch creation.
What is possibly causing this issue?
The producer is hitting timeout when latency reaches 120 seconds (default value of delivery.timeout.ms )
Why isnt the producer not learning about the throttle and quota and slowing down or backing off
What other producer configuration could help alleviate this timeout issue ?
(2048 * 4000) / 20480 = 400 (sec)
This means that, if your producer is trying to send the 4000 records full speed ( which is the case because you set throughput to -1), then it might batch them and put them in the queue.. in maybe one or two seconds (depending on your CPU).
Then, thanks to your quota settings (20480), you can be sure that the broker won't 'complete' the processing of those 4000 records before at least 399 or 398 seconds.
The broker does not return an error when a client exceeds its quota, but instead attempts to slow the client down. The broker computes the amount of delay needed to bring a client under its quota and delays the response for that amount of time.
Your request.timeout.ms being set to 120 seconds, you then have this timeoutException.
Can someone please explain on how is performance tested in Kafka using,
bin/kafka-consumer-perf-test.sh --topic benchmark-3-3-none \
--zookeeper kafka-zk-1:2181,kafka-zk-2:2181,kafka-zk-3:2181 \
--messages 15000000 \
--threads 1
and
bin/kafka-producer-perf-test.sh --topic benchmark-1-1-none \
--num-records 15000000 \
--record-size 100 \
--throughput 15000000 \
--producer-props \
acks=1 \
bootstrap.servers=kafka-kf-1:9092,kafka-kf-2:9092,kafka-kf-3:9092 \
buffer.memory=67108864 \
compression.type=none \
batch.size=8196
I am not clear on what are the paramters and what is the output that should be obtained. How will I check if I send 1000 messages to Kafka topics ,its performance and acknowledgement.
When we run this we get the following,
Producer
| start.time | end.time | compression | message.size | batch.size | total.data.sent.in.MB | MB.sec | total.data.sent.in.nMsg | nMsg.sec |
| 2016-02-03 21:38:28:094 | 2016-02-03 21:38:28:449 | 0 | 100 | 200 | 0.01 | 0.0269 | 100 | 281.6901 |
Where,
• total.data.sent.in.MB shows total data send to cluster in MB.
• MB.sec indicates how much data transferred in MB per sec(Throughput on size).
• total.data.sent.in.nMsg will show the count of total message which were sent during this test.
• And last nMsg.sec shows how many messages sent in a sec(Throughput on count of messages
Consumer
| start.time | end.time | fetch.size | data.consumed.in.MB | MB.sec | data.consumed.in.nMs | nMsg.sec |
| 2016-02-04 11:29:41:806 | 2016-02-04 11:29:46:854 | 1048576 | 0.0954 | 1.9869 | 1001 | 20854.1667
where,
• start.time, end.time will show when was test started and completed.
• fetch.size** shows the amount of data to fetch in a single request.
• data.consumed.in.MB**** shows the size of all messages consumed.
• ***MB.sec* indicates how much data transferred in MB per sec(Throughput on size).
• data.consumed.in.nMsg will show the count of total message which were consumed during this test.
• And last nMsg.sec shows how many messages consumed in a sec(Throughput on count of messages).
I would rather suggest going for a specialized performance testing tool like Apache JMeter and Pepper-Box - Kafka Load Generator in order to load test your Kafka installation.
This way you will be able to conduct the load having full control of threads, ramp-up time, message size and content, etc. You will also be able to generate HTML Reporting Dashboard having tables and charts with interesting metrics.
See Apache Kafka - How to Load Test with JMeter article for more details if needed.
If anyone runs into this question please note that kafka-producer-perf-test.sh should produce a different output as of Kafka v2.12-3.3.2.
For example, to send 1000 messages to a Kafka topic use command line parameter --num-records 1000 (and --topic <topic_name> of course). Generated output should resemble the following and include number of messages sent in steps, speed in terms of messages sent per second and MB per seconds, average latencies (I chose to send 1M messages):
323221 records sent, 64644.2 records/sec (63.13 MB/sec), 7.5 ms avg latency, 398.0 ms max latency.
381338 records sent, 76267.6 records/sec (74.48 MB/sec), 1.2 ms avg latency, 27.0 ms max latency.
1000000 records sent, 70244.450688 records/sec (68.60 MB/sec), 15.21 ms avg latency, 475.00 ms max latency, 1 ms 50th, 96 ms 95th, 353 ms 99th, 457 ms 99.9th.
I'm using 3 VM servers, each one has 16 core/ 56 GB Ram /1 TB, to setup a kafka cluster. I work with Kafka 0.10.0 version. I installed a broker on two of them. I have created a topic with 2 partitions, 1 partition/broker and without replication.
My goal is to attend 1 000 000 messages / second.
I made a test with kafka-producer-perf-test.sh script and i get between 150 000 msg/s and 204 000 msg/s.
My configuration is:
-batch size: 8k (8192)
-message size: 300 byte (0.3 KB)
-thread num: 1
The producer configuration:
-request.required.acks=1
-queue.buffering.max.ms=0 #linger.ms=0
-compression.codec=none
-queue.buffering.max.messages=100000
-send.buffer.bytes=100000000
Any help will be appreciated to get 1 000 000 msg / s
Thank you
You're running an old version of Apache Kafka. The most recent release (0.11) had improvements including around performance.
You might find this useful too: https://www.confluent.io/blog/optimizing-apache-kafka-deployment/
I have a Spark application that is now running for 46 hours. While majority of its jobs complete within 25 seconds, specific jobs take hours. Some details are provided below:
Task Time Shuffle Read Shuffle Write
7.5 h 2.2 MB / 257402 2.9 MB / 128601
There are other similar task times off-course having values of 11.3 h, 10.6 h, 9.4 h etc. each of them spending bulk of the activity time on "rdd at DataFrameFunctions.scala:42.". Details for the stage reveals that the time spent by executor on "Executor Computing time". This executor runs at DataNode 1, where the CPU utilization is very normal about 13%. Other boxes (4 more worker nodes) have very nominal CPU utilization.
When the Shuffle Read is within 5000 records, this is extremely fast and completes with 25 seconds, as stated previously. Nothing is appended to the logs (spark/hadoop/hbase), neither anything is noticed at /tmp or /var/tmp location which will indicate some disk related activity is in progress.
I am clueless about what is going wrong. Have been struggling with this for quite some time now. The versions of software used are as follows:
Hadoop : 2.7.2
Zookeeper : 3.4.9
Kafka : 2.11-0.10.1.1
Spark : 2.1.0
HBase : 1.2.6
Phoenix : 4.10.0
Some configurations on the spark default file.
spark.eventLog.enabled true
spark.eventLog.dir hdfs://SDCHDPMAST1:8111/data1/spark-event
spark.history.fs.logDirectory hdfs://SDCHDPMAST1:8111/data1/spark-event
spark.yarn.jars hdfs://SDCHDPMAST1:8111/user/appuser/spark/share/lib/*.jar
spark.driver.maxResultSize 5G
spark.deploy.zookeeper.url SDCZKPSRV01
spark.executor.memory 12G
spark.driver.memory 10G
spark.executor.heartbeatInterval 60s
spark.network.timeout 300s
Is there any way I can reduce the time spent on "Executor Computing time"?
The job performing on the specific dataset is skewed. Because of the skewness, jobs are taking more than expected.
What does running following Kafka tool actually give ?
./bin/kafka-run-class.sh org.apache.kafka.tools.ProducerPerformance --throughput=10000--topic=TOPIC--num-records=50000000 --record-size=200 --producer-props bootstrap.servers=SERVERS buffer.memory=67108864 batch.size=64000
When running with a single producer I get 90MB/s. When I use 3 separate producers on separate nodes I get only around 60 MB/s per producer. ( My Kafka cluster consists of 2 nodes, and topic has 6 partitions )
What does 90 MB/s mean? Is it the maximum rate at which a producer can produce?
Does partition count affect this value?
Why it drops to 60 MB/s when there are 3 producers ( still no network saturation on broker front)?
Thank you