Last active
February 6, 2018 16:59
-
-
Save arthurpham/88c12ce71664c90095a0ea0ec0212bac to your computer and use it in GitHub Desktop.
For Rancher # This compose file stands up Scrapy Cluster with an # associated ELK Stack. You should run a few crawls and then import the # `export.json` file into your Kibana objects
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
logstash-crawler: | |
labels: | |
io.rancher.container.pull_image: always | |
io.rancher.scheduler.affinity:container_label_soft_ne: io.rancher.stack_service.name=$$$${stack_name}/$$$${service_name} | |
io.rancher.scheduler.affinity:host_label: role=crawler | |
command: | |
- -f | |
- /etc/logstash/conf.d/logstash.conf | |
image: arthurpham/logstash-scrapy-cluster-docker:latest | |
links: | |
- 'kafka:' | |
- 'redis:' | |
- 'zookeeper:' | |
- 'elasticsearch:' | |
volumes_from: | |
- crawler | |
redis: | |
labels: | |
io.rancher.scheduler.affinity:host_label: role=redis | |
image: redis:latest | |
volumes: | |
- redisdata:/data | |
kafka-monitor: | |
environment: | |
LOG_DIR: /var/log/scrapy-cluster | |
LOG_JSON: 'True' | |
LOG_STDOUT: 'False' | |
REDIS_PORT: '6379' | |
labels: | |
io.rancher.sidekicks: logstash-kafka-monitor | |
io.rancher.scheduler.affinity:host_label: role=kafka_zookeeper | |
image: istresearch/scrapy-cluster:kafka-monitor-dev-alpine | |
links: | |
- 'kafka:' | |
- 'redis:' | |
- 'elasticsearch:' | |
volumes: | |
- /var/log/scrapy-cluster | |
logstash-redis-monitor: | |
labels: | |
io.rancher.container.pull_image: always | |
io.rancher.scheduler.affinity:host_label: role=redis | |
command: | |
- -f | |
- /etc/logstash/conf.d/logstash.conf | |
image: arthurpham/logstash-scrapy-cluster-docker:latest | |
links: | |
- 'kafka:' | |
- 'redis:' | |
- 'zookeeper:' | |
- 'elasticsearch:' | |
volumes_from: | |
- redis-monitor | |
zookeeper: | |
labels: | |
io.rancher.scheduler.affinity:host_label: role=kafka_zookeeper | |
image: wurstmeister/zookeeper:latest | |
logstash-kafka-monitor: | |
labels: | |
io.rancher.container.pull_image: always | |
io.rancher.scheduler.affinity:host_label: role=kafka_zookeeper | |
command: | |
- -f | |
- /etc/logstash/conf.d/logstash.conf | |
image: arthurpham/logstash-scrapy-cluster-docker:latest | |
links: | |
- 'kafka:' | |
- 'redis:' | |
- 'elasticsearch:' | |
volumes_from: | |
- kafka-monitor | |
kafka: | |
environment: | |
KAFKA_ADVERTISED_HOST_NAME: kafka | |
KAFKA_ADVERTISED_PORT: '9092' | |
KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: '1' | |
KAFKA_ZOOKEEPER_CONNECT: zookeeper:2181 | |
KAFKA_LOG_RETENTION_BYTES: '1073741824' | |
KAFKA_LOG_SEGMENT_BYTES: '536870912' | |
KAFKA_LOG_RETENTION_CHECK_INTERVAL: '60000' | |
labels: | |
io.rancher.scheduler.affinity:container_label_soft_ne: io.rancher.stack_service.name=$${stack_name}/elasticsearch | |
io.rancher.scheduler.affinity:host_label: role=kafka_zookeeper | |
image: wurstmeister/kafka:latest | |
links: | |
- 'zookeeper:' | |
volumes: | |
- /var/run/docker.sock:/var/run/docker.sock | |
kibana: | |
ports: | |
- 5601:5601/tcp | |
environment: | |
NODE_OPTIONS: --max-old-space-size=200 | |
labels: | |
io.rancher.container.pull_image: always | |
io.rancher.scheduler.affinity:host_label: role=elk | |
image: kibana:4 | |
links: | |
- 'elasticsearch:' | |
crawler: | |
environment: | |
REDIS_PORT: '6379' | |
SC_LOG_DIR: /var/log/scrapy-cluster | |
SC_LOG_JSON: 'True' | |
SC_LOG_STDOUT: 'False' | |
QUEUE_HITS: '20' | |
QUEUE_WINDOW: '60' | |
labels: | |
io.rancher.sidekicks: logstash-crawler | |
io.rancher.scheduler.affinity:container_label_soft_ne: io.rancher.stack_service.name=$$$${stack_name}/$$$${service_name} | |
io.rancher.scheduler.affinity:host_label: role=crawler | |
image: istresearch/scrapy-cluster:crawler-dev-alpine | |
links: | |
- 'kafka:' | |
- 'redis:' | |
- 'zookeeper:' | |
- 'elasticsearch:' | |
volumes: | |
- /var/log/scrapy-cluster | |
redis-monitor: | |
environment: | |
LOG_DIR: /var/log/scrapy-cluster | |
LOG_JSON: 'True' | |
LOG_STDOUT: 'False' | |
REDIS_PORT: '6379' | |
labels: | |
io.rancher.sidekicks: logstash-redis-monitor | |
io.rancher.scheduler.affinity:host_label: role=redis | |
image: istresearch/scrapy-cluster:redis-monitor-dev-alpine | |
links: | |
- 'kafka:' | |
- 'redis:' | |
- 'zookeeper:' | |
- 'elasticsearch:' | |
volumes: | |
- /var/log/scrapy-cluster | |
elasticsearch: | |
environment: | |
ES_JAVA_OPTS: -Xms1g -Xmx1g | |
ES_NETWORK_HOST: 0.0.0.0 | |
labels: | |
io.rancher.scheduler.affinity:container_label_soft_ne: io.rancher.stack_service.name=$${stack_name}/kafka | |
io.rancher.container.pull_image: always | |
io.rancher.scheduler.affinity:host_label: role=elk | |
command: | |
- elasticsearch | |
image: elasticsearch:2 | |
volumes: | |
- esdata:/usr/share/elasticsearch/data |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment