Skip to content

Instantly share code, notes, and snippets.

@saurabhmishra
Forked from jkreps/benchmark-commands.txt
Last active August 12, 2019 14:24
Show Gist options
  • Star 9 You must be signed in to star a gist
  • Fork 9 You must be signed in to fork a gist
  • Save saurabhmishra/6ed428be4c00003dd926 to your computer and use it in GitHub Desktop.
Save saurabhmishra/6ed428be4c00003dd926 to your computer and use it in GitHub Desktop.
Kafka Benchmark Commands
Producer
Setup
bin/kafka-topics.sh --zookeeper zookeeper_server:2181 --create --topic test-rep-one --partitions 6 --replication-factor 1
bin/kafka-topics.sh --zookeeper zookeeper_server:2181 --create --topic test --partitions 6 --replication-factor 3
Single thread, no replication
bin/kafka-run-class.sh org.apache.kafka.clients.tools.ProducerPerformance test7 50000000 100 -1 acks=1 bootstrap.servers=kafka_server:6667 buffer.memory=67108864 batch.size=8196
Single-thread, async 3x replication
bin/kafktopics.sh --zookeeper zookeeper_server:2181 --create --topic test --partitions 6 --replication-factor 3
bin/kafka-run-class.sh org.apache.kafka.clients.tools.ProducerPerformance test6 50000000 100 -1 acks=1 bootstrap.servers=kafka_server:6667 buffer.memory=67108864 batch.size=8196
Single-thread, sync 3x replication
bin/kafka-run-class.sh org.apache.kafka.clients.tools.ProducerPerformance test 50000000 100 -1 acks=-1 bootstrap.servers=kafka_server:6667 buffer.memory=67108864 batch.size=64000
Three Producers, 3x async replication
bin/kafka-run-class.sh org.apache.kafka.clients.tools.ProducerPerformance test 50000000 100 -1 acks=1 bootstrap.servers=kafka_server:6667 buffer.memory=67108864 batch.size=8196
Throughput Versus Stored Data
bin/kafka-run-class.sh org.apache.kafka.clients.tools.ProducerPerformance test 50000000000 100 -1 acks=1 bootstrap.servers=kafka_server:6667 buffer.memory=67108864 batch.size=8196
Effect of message size
for i in 10 100 1000 10000 100000;
do
echo ""
echo $i
bin/kafka-run-class.sh org.apache.kafka.clients.tools.ProducerPerformance test $((1000*1024*1024/$i)) $i -1 acks=1 bootstrap.servers=kafka_server:6667 buffer.memory=67108864 batch.size=128000
done;
Consumer
Consumer throughput
bin/kafka-consumer-perf-test.sh --zookeeper zookeeper_server:2181 --messages 50000000 --topic test --threads 1
3 Consumers
On three servers, run:
bin/kafka-consumer-perf-test.sh --zookeeper zookeeper_server:2181 --messages 50000000 --topic test --threads 1
End-to-end Latency
bin/kafka-run-class.sh kafka.tools.TestEndToEndLatency kafka_server:6667 zookeeper_server:2181 test 5000 100 1
Producer and consumer
bin/kafka-run-class.sh org.apache.kafka.clients.tools.ProducerPerformance test 50000000 100 -1 acks=1 bootstrap.servers=kafka_server:6667 buffer.memory=67108864 batch.size=8196
bin/kafka-consumer-perf-test.sh --zookeeper zookeeper_server:2181 --messages 50000000 --topic test --threads 1
End-to-end Latency
0.0543 ms ms (median)
0.003125 ms (99th percentile)
5 ms (99.9th percentile)
Producer and consumer
Producer - 1431170.2 records/sec (136.49 MB/sec)
Consumer - 3276754.7021 records/sec (312.4957 MB/sec)
Setup
5 Kafka Broker
5 Zookeeper
32 core
10 Disk Jbod ext4
190GB memory
10GB Network Dual Bounded
#!/bin/bash
# Set KAFKA specific environment variables here.
# The java implementation to use.
export JAVA_HOME={{java64_home}}
export PATH=$PATH:$JAVA_HOME/bin
export PID_DIR={{kafka_pid_dir}}
export LOG_DIR={{kafka_log_dir}}
export JMX_PORT=9093
export KAFKA_HEAP_OPTS="-Xmx16g -Xms16g"
export KAFKA_JVM_PERFORMANCE_OPTS="-XX:MetaspaceSize=96m -XX:+UseG1GC
-XX:MaxGCPauseMillis=20 -XX:InitiatingHeapOccupancyPercent=35 -XX:G1HeapRegionSize=16M
-XX:MinMetaspaceFreeRatio=50 -XX:MaxMetaspaceFreeRatio=80"
# Add kafka sink to classpath and related depenencies
if [ -e "/usr/lib/ambari-metrics-kafka-sink/ambari-metrics-kafka-sink.jar" ]; then
export CLASSPATH=$CLASSPATH:/usr/lib/ambari-metrics-kafka-sink/ambari-metrics-kafka-sink.jar
export CLASSPATH=$CLASSPATH:/usr/lib/ambari-metrics-kafka-sink/lib/*
fi
# Generated by Apache Ambari.
auto.create.topics.enable=true
auto.leader.rebalance.enable=true
broker.id=0
compression.type=producer
controlled.shutdown.enable=true
controlled.shutdown.max.retries=3
controlled.shutdown.retry.backoff.ms=5000
controller.message.queue.size=10
controller.socket.timeout.ms=30000
default.replication.factor=1
delete.topic.enable=false
external.kafka.metrics.exclude.prefix=kafka.network.RequestMetrics,kafka.server.DelayedOperationPurgatory,kafka.server.BrokerTopicMetrics.BytesRejectedPerSec
external.kafka.metrics.include.prefix=kafka.network.RequestMetrics.ResponseQueueTimeMs.request.OffsetCommit.98percentile,kafka.network.RequestMetrics.ResponseQueueTimeMs.request.
Offsets.95percentile,kafka.network.RequestMetrics.ResponseSendTimeMs.request.Fetch.95percentile,kafka.network.RequestMetrics.RequestsPerSec.request
fetch.purgatory.purge.interval.requests=10000
kafka.ganglia.metrics.group=kafka
kafka.ganglia.metrics.host=localhost
kafka.ganglia.metrics.port=8671
kafka.ganglia.metrics.reporter.enabled=true
kafka.metrics.reporters=org.apache.hadoop.metrics2.sink.kafka.KafkaTimelineMetricsReporter
kafka.timeline.metrics.host=blah
kafka.timeline.metrics.maxRowCacheSize=10000
kafka.timeline.metrics.port=6188
kafka.timeline.metrics.reporter.enabled=true
kafka.timeline.metrics.reporter.sendInterval=5900
leader.imbalance.check.interval.seconds=300
leader.imbalance.per.broker.percentage=10
listeners=PLAINTEXT://kafka1:6667
log.cleanup.interval.mins=10
log.dirs=/data/vol5/kafka-logs,/data/vol11/kafka-logs,/data/vol6/kafka-logs,/data/vol10/kafka-logs,/data/vol8/kafka-logs,/data/vol7/kafka-logs,/data/vol12/kafka-logs,/data/vol9/k
afka-logs,/data/vol4/kafka-logs,/data/vol3/kafka-logs
log.flush.interval.messages=10000
log.flush.interval.ms=3000
log.flush.scheduler.interval.ms=3000
log.index.interval.bytes=4096
log.index.size.max.bytes=10485760
log.retention.bytes=100000000000
log.retention.hours=24
log.roll.hours=24
log.segment.bytes=1073741824
message.max.bytes=6300000
min.insync.replicas=1
num.io.threads=18
num.network.threads=24
num.partitions=8
num.recovery.threads.per.data.dir=1
num.replica.fetchers=1
offset.metadata.max.bytes=4096
offsets.commit.required.acks=-1
offsets.commit.timeout.ms=5000
offsets.load.buffer.size=5242880
offsets.retention.check.interval.ms=600000
offsets.retention.minutes=86400000
offsets.topic.compression.codec=0
offsets.topic.num.partitions=50
offsets.topic.replication.factor=3
offsets.topic.segment.bytes=104857600
port=6667
producer.purgatory.purge.interval.requests=10000
queued.max.requests=500
replica.fetch.max.bytes=6348576
replica.fetch.min.bytes=1
replica.fetch.wait.max.ms=500
replica.high.watermark.checkpoint.interval.ms=5000
replica.lag.max.messages=10000000
replica.lag.time.max.ms=10000
replica.socket.receive.buffer.bytes=1048576
replica.socket.timeout.ms=30000
socket.receive.buffer.bytes=102400
socket.request.max.bytes=104857600
socket.send.buffer.bytes=1048576
zookeeper.connect=zk1:2181,zk2:2181,zk3:2181,zk4:2181,zk5:2181
zookeeper.connection.timeout.ms=1000000
zookeeper.session.timeout.ms=30000
zookeeper.sync.time.ms=2000
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment