I have a strange problem. I am sending the logs of my kubernetes cluster to Kafka using Fluentd. Everything works fine when I tell Fluentd to send the messages to a single topic partition. But when I tell Fluentd to distribute the messages in the different partitions that topic has, then it throws errors indicating that the messages are corrupted.
I've done a lot of reading and I'm pretty sure it's a problem in my kafka cluster and not in Fluentd. But I really don't know, the strongest theory I have is that there is a problem with the offset, sadly I don't know much about kafka.
Any idea what is happening?
This is my kafka configuration:
---
apiVersion: v1
kind: Service
metadata:
name: kafka-hs
labels:
app: kafka
spec:
ports:
- port: 9092
name: server
protocol: TCP
clusterIP: None
selector:
app: kafka
---
apiVersion: policy/v1
kind: PodDisruptionBudget
metadata:
name: kafka-pdb
spec:
selector:
matchLabels:
app: kafka
maxUnavailable: 1
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: kafka
spec:
selector:
matchLabels:
app: kafka
serviceName: kafka-hs
replicas: 3
podManagementPolicy: Parallel
updateStrategy:
type: RollingUpdate
template:
metadata:
labels:
app: kafka
spec:
nodeSelector:
role: bitmaker-kafka
containers:
- name: k8skafka
imagePullPolicy: Always
image: fastop/kafka:2.2.0
ports:
- containerPort: 9092
name: server
command:
- sh
- -c
- "exec kafka-server-start.sh /opt/kafka/config/server.properties --override broker.id=${HOSTNAME##*-} \
--override listeners=PLAINTEXT://:9092 \
--override zookeeper.connect=zk-cs.default.svc.cluster.local:2181 \
--override log.dir=/var/lib/kafka \
--override auto.create.topics.enable=true \
--override auto.leader.rebalance.enable=true \
--override background.threads=10 \
--override compression.type=producer \
--override delete.topic.enable=false \
--override leader.imbalance.check.interval.seconds=300 \
--override leader.imbalance.per.broker.percentage=10 \
--override log.flush.interval.messages=9223372036854775807 \
--override log.flush.offset.checkpoint.interval.ms=60000 \
--override log.flush.scheduler.interval.ms=9223372036854775807 \
--override log.retention.bytes=-1 \
--override log.retention.hours=168 \
--override log.roll.hours=168 \
--override log.roll.jitter.hours=0 \
--override log.segment.bytes=1073741824 \
--override log.segment.delete.delay.ms=60000 \
--override message.max.bytes=1000012 \
--override min.insync.replicas=1 \
--override num.io.threads=8 \
--override num.network.threads=3 \
--override num.recovery.threads.per.data.dir=1 \
--override num.replica.fetchers=1 \
--override offset.metadata.max.bytes=4096 \
--override offsets.commit.required.acks=-1 \
--override offsets.commit.timeout.ms=5000 \
--override offsets.load.buffer.size=5242880 \
--override offsets.retention.check.interval.ms=600000 \
--override offsets.retention.minutes=1440 \
--override offsets.topic.compression.codec=0 \
--override offsets.topic.num.partitions=50 \
--override offsets.topic.replication.factor=3 \
--override offsets.topic.segment.bytes=104857600 \
--override queued.max.requests=500 \
--override quota.consumer.default=9223372036854775807 \
--override quota.producer.default=9223372036854775807 \
--override replica.fetch.min.bytes=1 \
--override replica.fetch.wait.max.ms=500 \
--override replica.high.watermark.checkpoint.interval.ms=5000 \
--override replica.lag.time.max.ms=10000 \
--override replica.socket.receive.buffer.bytes=65536 \
--override replica.socket.timeout.ms=30000 \
--override request.timeout.ms=30000 \
--override socket.receive.buffer.bytes=102400 \
--override socket.request.max.bytes=104857600 \
--override socket.send.buffer.bytes=102400 \
--override unclean.leader.election.enable=true \
--override zookeeper.session.timeout.ms=6000 \
--override zookeeper.set.acl=false \
--override broker.id.generation.enable=true \
--override connections.max.idle.ms=600000 \
--override controlled.shutdown.enable=true \
--override controlled.shutdown.max.retries=3 \
--override controlled.shutdown.retry.backoff.ms=5000 \
--override controller.socket.timeout.ms=30000 \
--override default.replication.factor=1 \
--override fetch.purgatory.purge.interval.requests=1000 \
--override group.max.session.timeout.ms=300000 \
--override group.min.session.timeout.ms=6000 \
--override inter.broker.protocol.version=2.2.0 \
--override log.cleaner.backoff.ms=15000 \
--override log.cleaner.dedupe.buffer.size=134217728 \
--override log.cleaner.delete.retention.ms=86400000 \
--override log.cleaner.enable=true \
--override log.cleaner.io.buffer.load.factor=0.9 \
--override log.cleaner.io.buffer.size=524288 \
--override log.cleaner.io.max.bytes.per.second=1.7976931348623157E308 \
--override log.cleaner.min.cleanable.ratio=0.5 \
--override log.cleaner.min.compaction.lag.ms=0 \
--override log.cleaner.threads=1 \
--override log.cleanup.policy=delete \
--override log.index.interval.bytes=4096 \
--override log.index.size.max.bytes=10485760 \
--override log.message.timestamp.difference.max.ms=9223372036854775807 \
--override log.message.timestamp.type=CreateTime \
--override log.preallocate=false \
--override log.retention.check.interval.ms=300000 \
--override max.connections.per.ip=2147483647 \
--override num.partitions=5 \
--override producer.purgatory.purge.interval.requests=1000 \
--override replica.fetch.backoff.ms=1000 \
--override replica.fetch.max.bytes=1048576 \
--override replica.fetch.response.max.bytes=10485760 \
--override reserved.broker.max.id=1000 "
env:
- name: KAFKA_HEAP_OPTS
value : "-Xmx512M -Xms512M"
- name: KAFKA_OPTS
value: "-Dlogging.level=INFO"
volumeMounts:
- name: datadir
mountPath: /var/lib/kafka
securityContext:
runAsUser: 1000
fsGroup: 1000
volumeClaimTemplates:
- metadata:
name: datadir
spec:
accessModes: [ "ReadWriteOnce" ]
resources:
requests:
storage: 5Gi
storageClassName: do-block-storage
My zookeeper configuration:
---
apiVersion: v1
kind: Service
metadata:
name: zk-hs
labels:
app: zk
spec:
ports:
- port: 2888
name: follower
protocol: TCP
- port: 3888
name: leader
protocol: TCP
clusterIP: None
selector:
app: zk
---
apiVersion: v1
kind: Service
metadata:
name: zk-cs
labels:
app: zk
spec:
ports:
- port: 2181
name: client
selector:
app: zk
---
apiVersion: policy/v1
kind: PodDisruptionBudget
metadata:
name: zk-pdb
spec:
selector:
matchLabels:
app: zk
maxUnavailable: 1
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: zk
spec:
selector:
matchLabels:
app: zk
serviceName: zk-hs
replicas: 3
updateStrategy:
type: RollingUpdate
podManagementPolicy: Parallel
updateStrategy:
type: RollingUpdate
template:
metadata:
labels:
app: zk
spec:
nodeSelector:
role: bitmaker-kafka
containers:
- name: kubernetes-zookeeper
imagePullPolicy: Always
image: fastop/zookeeper:3.4.10
ports:
- containerPort: 2181
name: client
- containerPort: 2888
name: follower
- containerPort: 3888
name: leader
command:
- sh
- -c
- "start-zookeeper \
--servers=3 \
--data_dir=/var/lib/zookeeper/data \
--data_log_dir=/var/lib/zookeeper/data/log \
--conf_dir=/opt/zookeeper/conf \
--client_port=2181 \
--election_port=3888 \
--server_port=2888 \
--tick_time=2000 \
--init_limit=10 \
--sync_limit=5 \
--heap=512M \
--max_client_cnxns=60 \
--snap_retain_count=3 \
--purge_interval=12 \
--max_session_timeout=40000 \
--min_session_timeout=4000 \
--log_level=INFO"
readinessProbe:
exec:
command:
- sh
- -c
- "zookeeper-ready 2181"
initialDelaySeconds: 10
timeoutSeconds: 5
livenessProbe:
exec:
command:
- sh
- -c
- "zookeeper-ready 2181"
initialDelaySeconds: 10
timeoutSeconds: 5
volumeMounts:
- name: datadir
mountPath: /var/lib/zookeeper
securityContext:
runAsUser: 1000
fsGroup: 1000
volumeClaimTemplates:
- metadata:
name: datadir
spec:
accessModes: [ "ReadWriteOnce" ]
resources:
requests:
storage: 5Gi
storageClassName: do-block-storage
And this is my my fluentd configuration:
apiVersion: v1
kind: ConfigMap
metadata:
name: fluentdconf
namespace: kube-system
data:
fluent.conf: |
<source>
@type tail
@id in_tail_container_logs
path "/var/log/containers/*.log"
pos_file "/var/log/fluentd-containers.log.pos"
tag "kubernetes.*"
exclude_path []
read_from_head true
<parse>
@type "/^(?<time>.+) (?<stream>stdout|stderr)( (?<logtag>.))? (?<log>.*)$/"
time_format "%Y-%m-%dT%H:%M:%S.%NZ"
unmatched_lines
expression ^(?<time>.+) (?<stream>stdout|stderr)( (?<logtag>.))? (?<log>.*)$
ignorecase false
multiline false
</parse>
</source>
<match fluent.**>
@type null
</match>
<filter kubernetes.**>
@type kubernetes_metadata
skip_container_metadata true
skip_master_url true
skip_namespace_metadata true
skip_labels true
</filter>
<match kubernetes.var.log.containers.**fluentd**.log>
@type null
</match>
<match kubernetes.var.log.containers.**kube-system**.log>
@type null
</match>
<match kubernetes.var.log.containers.**jobcontainer**.log>
@type kafka2
@id out_kafka2
brokers kafka-0.kafka-hs.default.svc.cluster.local:9092,kafka-1.kafka-hs.default.svc.cluster.local:9092,kafka-2.kafka-hs.default.svc.cluster.local:9092
default_topic "testlogs"
get_kafka_client_log true
max_send_retries 1
required_acks -1
max_send_limit_bytes 100000000
compression_codec "gzip"
ack_timeout
discard_kafka_delivery_failed false
share_producer true
<format>
@type "json"
</format>
</match>
En this is my daemonset for fluentd:
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: fluentd
namespace: kube-system
labels:
k8s-app: fluentd-logging
version: v1
kubernetes.io/cluster-service: "true"
spec:
selector:
matchLabels:
k8s-app: fluentd-logging
template:
metadata:
labels:
k8s-app: fluentd-logging
version: v1
kubernetes.io/cluster-service: "true"
spec:
serviceAccount: fluentd
serviceAccountName: fluentd
tolerations:
- key: node-role.kubernetes.io/master
effect: NoSchedule
containers:
- name: fluentd
image: fluent/fluentd-kubernetes-daemonset:v1.11-debian-kafka2-1
env:
- name: FLUENT_KAFKA_BROKERS
value: "kafka-1.kafka-hs.default.svc.cluster.local:9092"
- name: FLUENT_KAFKA_DEFAULT_TOPIC
value: "testlogs"
- name: FLUENT_CONTAINER_TAIL_PARSER_TYPE
value: /^(?<time>.+) (?<stream>stdout|stderr)( (?<logtag>.))? (?<log>.*)$/
- name: FLUENT_KAFKA_COMPRESSION_CODEC
value: "gzip"
- name: FLUENT_KAFKA_MAX_SEND_LIMIT_BYTES
value: "1000000"
- name: FLUENT_KAFKA_REQUIRED_ACKS
value: "1"
- name: K8S_NODE_NAME
value: "bitmaker-workers"
resources:
limits:
memory: 200Mi
requests:
cpu: 100m
memory: 200Mi
volumeMounts:
- name: fluentconfig
mountPath: /fluentd/etc/
- name: varlog
mountPath: /var/log
- name: varlibdockercontainers
mountPath: /var/lib/docker/containers
readOnly: true
terminationGracePeriodSeconds: 30
volumes:
- name: fluentconfig
configMap:
name: fluentdconf
- name: varlog
hostPath:
path: /var/log
- name: varlibdockercontainers
hostPath:
path: /var/lib/docker/containers
