1 {%- if pillar.elasticsearch.server is defined or pillar.elasticsearch.client is defined %}
2 {%- from "elasticsearch/map.jinja" import server, client, monitoring with context %}
6 {%- if client.get('enabled', False) %}
7 ElasticsearchClusterHealthStatusMajor:
9 elasticsearch_cluster_health_status == 2
14 service: elasticsearch
16 summary: "Elasticsearch cluster status is YELLOW"
17 description: "The Elasticsearch cluster status is YELLOW for 2 minutes."
19 ElasticsearchClusterHealthStatusCritical:
21 elasticsearch_cluster_health_status == 3
26 service: elasticsearch
28 summary: "Elasticsearch cluster status is RED"
29 description: "The Elasticsearch cluster status is RED for 2 minutes."
31 ElasticsearchIndicesInReadOnlyMode:
33 exec_elasticsearch_indices_read_only_allow_delete > 0
38 service: elasticsearch
40 summary: "Elasticsearch indices are read-only"
41 description: "The Elasticsearch service has indices in read-only mode for 2 minutes."
44 {%- if server.get('enabled', False) %}
45 ElasticsearchServiceDown:
47 elasticsearch_up{host=~'.*'} == 0
51 service: elasticsearch
53 summary: "Elasticsearch service is down"
54 description: "The Elasticsearch service on the {{ $labels.host }} node is down."
56 ElasticsearchServiceDownMinor:
58 count(elasticsearch_up{host=~'.*'} == 0) >= count(elasticsearch_up{host=~'.*'}) * {{ monitoring.service_failed_warning_threshold_percent }}
63 service: elasticsearch
65 summary: "{%- endraw %}{{monitoring.service_failed_warning_threshold_percent*100}}%{%- raw %} of Elasticsearch services are down"
66 description: "{{ $value }} Elasticsearch services are down for 2 minutes."
68 ElasticsearchServiceDownMajor:
70 count(elasticsearch_up{host=~'.*'} == 0) >= count(elasticsearch_up{host=~'.*'}) * {{ monitoring.service_failed_critical_threshold_percent }}
75 service: elasticsearch
77 summary: "{%- endraw %}{{monitoring.service_failed_critical_threshold_percent*100}}%{%- raw %} of Elasticsearch services are down"
78 description: "{{ $value }} Elasticsearch services are down for 2 minutes."
80 ElasticsearchServiceOutage:
82 count(elasticsearch_up{host=~'.*'} == 0) == count(elasticsearch_up{host=~'.*'})
86 service: elasticsearch
88 summary: "Elasticsearch cluster outage"
89 description: "All Elasticsearch services within the cluster are down."
91 ElasticsearchDiskWaterMarkMinor:
93 (max(elasticsearch_fs_total_total_in_bytes) by (host, instance) - max(elasticsearch_fs_total_available_in_bytes) by (host, instance)) / max(elasticsearch_fs_total_total_in_bytes) by (host, instance) >= {{monitoring.service_disk_space_watermark_minor_threshold_percent}}
98 service: elasticsearch
100 summary: "Elasticsearch uses {%- endraw %} {{monitoring.service_disk_space_watermark_minor_threshold_percent*100}}%{%- raw %} of disk space"
101 description: "The Elasticsearch '{{ $labels.instance }}' instance uses {{ $value }}% of disk space on the {{ $labels.host }} node for 5 minutes."
103 ElasticsearchDiskWaterMarkMajor:
105 (max(elasticsearch_fs_total_total_in_bytes) by (host, instance) - max(elasticsearch_fs_total_available_in_bytes) by (host, instance)) / max(elasticsearch_fs_total_total_in_bytes) by (host, instance) >= {{monitoring.service_disk_space_watermark_major_threshold_percent}}
110 service: elasticsearch
112 summary: "Elasticsearch uses {%- endraw %} {{monitoring.service_disk_space_watermark_major_threshold_percent*100}}%{%- raw %} of disk space"
113 description: "The Elasticsearch '{{ $labels.instance }}' instance uses {{ $value }}% of disk space on the {{ $labels.host }} node for 5 minutes."