Prometheus系列 | 监控elasticsearch

wget https://github.com/justwatchcom/elasticsearch_exporter/releases/download/v1.0.4rc1/elasticsearch_exporter-1.0.4rc1.linux-amd64.tar.gz

 tar -zxvf elasticsearch_exporter-1.0.4rc1.linux-amd64.tar.gz
 cd elasticsearch_exporter-1.0.4rc1.linux-amd64/
 nohup ./elasticsearch_exporter --web.listen-address ":9109"  --es.uri http://192.168.50.153:9200 &

- job_name: 'elasticsearch'
      scrape_interval: 60s
      scrape_timeout:  30s
      metrics_path: "/metrics"
      static_configs:
      - targets:
        - '192.168.50.153:9109'
        labels:
          service: elasticsearch
      relabel_configs:
      - source_labels: [__address__]
        regex: '(.*)\:9109'
        target_label:  'instance'
        replacement:   '$1'
      - source_labels: [__address__]
        regex:         '.*\.(.*)\.lan.*'
        target_label:  'environment'
        replacement:   '$1'

./reload-prometheus.sh

https://grafana.com/dashboards/2322

groups:
- name: elasticsearchStatsAlert
  rules:
  - alert: Elastic_Cluster_Health_RED
    expr: elasticsearch_cluster_health_status{color="red"}==1
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: "Instance {{ $labels.instance }}: not all primary and replica shards are allocated in elasticsearch cluster {{ $labels.cluster }}"
      description: "Instance {{ $labels.instance }}: not all primary and replica shards are allocated in elasticsearch cluster {{ $labels.cluster }}."
  - alert: Elastic_Cluster_Health_Yellow
    expr: elasticsearch_cluster_health_status{color="yellow"}==1
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: " Instance {{ $labels.instance }}: not all primary and replica shards are allocated in elasticsearch cluster {{ $labels.cluster }}"
      description: "Instance {{ $labels.instance }}: not all primary and replica shards are allocated in elasticsearch cluster {{ $labels.cluster }}."
  - alert: Elasticsearch_JVM_Heap_Too_High
    expr: elasticsearch_jvm_memory_used_bytes{area="heap"} / elasticsearch_jvm_memory_max_bytes{area="heap"} > 0.8
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: "ElasticSearch node {{ $labels.instance }} heap usage is high "
      description: "The heap in {{ $labels.instance }} is over 80% for 15m."
  - alert: Elasticsearch_health_up
    expr: elasticsearch_cluster_health_up !=1
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: " ElasticSearch node: {{ $labels.instance }} last scrape of the ElasticSearch cluster health failed"
      description: "ElasticSearch node: {{ $labels.instance }} last scrape of the ElasticSearch cluster health failed"
  - alert: Elasticsearch_Too_Few_Nodes_Running
    expr: elasticsearch_cluster_health_number_of_nodes < 12
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: "There are only {{$value}} < 12 ElasticSearch nodes running "
      description: "lasticSearch running on less than 12 nodes(total 14)"
  - alert: Elasticsearch_Count_of_JVM_GC_Runs
    expr: rate(elasticsearch_jvm_gc_collection_seconds_count{}[5m])>5
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: "ElasticSearch node {{ $labels.instance }}: Count of JVM GC runs > 5 per sec and has a value of {{ $value }} "
      description: "ElasticSearch node {{ $labels.instance }}: Count of JVM GC runs > 5 per sec and has a value of {{ $value }}"
  - alert: Elasticsearch_GC_Run_Time
    expr: rate(elasticsearch_jvm_gc_collection_seconds_sum[5m])>0.3
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: " ElasticSearch node {{ $labels.instance }}: GC run time in seconds > 0.3 sec and has a value of {{ $value }}"
      description: "ElasticSearch node {{ $labels.instance }}: GC run time in seconds > 0.3 sec and has a value of {{ $value }}"
  - alert: Elasticsearch_json_parse_failures
    expr: elasticsearch_cluster_health_json_parse_failures>0
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: " ElasticSearch node {{ $labels.instance }}: json parse failures > 0 and has a value of {{ $value }}"
      description: "ElasticSearch node {{ $labels.instance }}: json parse failures > 0 and has a value of {{ $value }}"
  - alert: Elasticsearch_breakers_tripped
    expr: rate(elasticsearch_breakers_tripped{}[5m])>0
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: " ElasticSearch node {{ $labels.instance }}: breakers tripped > 0 and has a value of {{ $value }}"
      description: "ElasticSearch node {{ $labels.instance }}: breakers tripped > 0 and has a value of {{ $value }}"
  - alert: Elasticsearch_health_timed_out
    expr: elasticsearch_cluster_health_timed_out>0
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: " ElasticSearch node {{ $labels.instance }}: Number of cluster health checks timed out > 0 and has a value of {{ $value }}"
      description: "ElasticSearch node {{ $labels.instance }}: Number of cluster health checks timed out > 0 and has a value of {{ $value }}"

Since Elasticsearch 7.0.0 : ./bin/elasticsearch-plugin install -b https://github.com/vvanholl/elasticsearch-prometheus-exporter/releases/download/7.2.1.0/prometheus-exporter-7.2.1.0.zip

Since Elasticsearch 6.0.0 : ./bin/elasticsearch-plugin install -b https://github.com/vvanholl/elasticsearch-prometheus-exporter/releases/download/6.8.0.0/prometheus-exporter-6.8.0.0.zip

On Elasticsearch 5.x.x : ./bin/elasticsearch-plugin install -b https://github.com/vvanholl/elasticsearch-prometheus-exporter/releases/download/5.6.16.0/elasticsearch-prometheus-exporter-5.6.16.0.zip

On old 2.x.x versions : ./bin/plugin install https://github.com/vvanholl/elasticsearch-prometheus-exporter/releases/download/2.4.1.0/elasticsearch-prometheus-exporter-2.4.1.0.zip

Do not forget to restart the node after the installation!

Note that the plugin needs the following special permissions:

java.lang.RuntimePermission accessClassInPackage.sun.misc
java.lang.RuntimePermission accessDeclaredMembers
java.lang.reflect.ReflectPermission suppressAccessChecks
If you have a lot of indices and think this data is irrelevant, you can disable in the main configuration file:

prometheus.indices: false
To disable exporting cluster settings use:

prometheus.cluster.settings: false

Uninstall
Since Elasticsearch 6.0.0: ./bin/elasticsearch-plugin remove prometheus-exporter

On Elasticsearch 5.x.x: ./bin/elasticsearch-plugin remove prometheus-exporter

On old 2.x.x versions: ./bin/plugin remove prometheus-exporter

- job_name: elasticsearch
  scrape_interval: 10s
  metrics_path: "/_prometheus/metrics"
  static_configs:
  - targets:
    - node1:9200
    - node2:9200
    - node3:9200

- job_name: 'elastic-cluster'
      scrape_interval: 10s
      metrics_path: '/_prometheus/metrics'
      static_configs:
      - targets:
        - 'node1:9200'
        - 'node2:9200'
        - 'node3:9200'
      basic_auth:
        username: 'elastic'
        password: 'elastic'