From 9e5a29546562773d7c244f961cba254302f6c785 Mon Sep 17 00:00:00 2001
From: Steve Wilkerson <wilkers.steve@gmail.com>
Date: Wed, 16 Jan 2019 11:00:25 -0600
Subject: [PATCH] Update Elasticsearch health status expressions

This updates the Elasticsearch health status expressions used in
Prometheus, Nagios and Grafana.  The previous Prometheus rule
defined for Elasticsearch health checked for a status that was
> 0 to trigger an alarm for a green health status. The correct
returned values are: 1 for green, 0 for both red and yellow. This
changes the expression to use arithmetic operators to give us a
result that maps to: 2 for green, 1 for yellow, 0 for red.

This also updates the Elasticsearch dashboard in Grafana to add a
new mapping for the updated 2g,1y,0r scale.

Finally, this also updates the Nagios service check to be a bit
more verbose in its output.

For reference, see:
https://github.com/justwatchcom/elasticsearch_exporter/issues/120

Change-Id: I6ef2a7c308c6ebfdb693b46127a285bceb6ba872
---
 grafana/values.yaml    |  9 ++++++---
 nagios/values.yaml     |  2 +-
 prometheus/values.yaml | 12 ++++++++++--
 3 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/grafana/values.yaml b/grafana/values.yaml
index f1cce35b2..c1272c61a 100644
--- a/grafana/values.yaml
+++ b/grafana/values.yaml
@@ -5805,14 +5805,14 @@ conf:
             show: true
           tableColumn: ''
           targets:
-          - expr: sum(elasticsearch_cluster_health_status{cluster=~"$cluster"})
+          - expr: (sum(elasticsearch_cluster_health_status{cluster=~"$cluster",color="green"})*2)+sum(elasticsearch_cluster_health_status{cluster=~"$cluster",color="yellow"})
             format: time_series
-            intervalFactor: 2
+            intervalFactor: 3
             legendFormat: ''
             metric: ''
             refId: A
             step: 40
-          thresholds: '0,1'
+          thresholds: '0,1,2'
           title: Cluster health status
           transparent: false
           type: singlestat
@@ -5820,6 +5820,9 @@ conf:
           valueMaps:
           - op: "="
             text: GREEN
+            value: '2'
+          - op: "="
+            text: YELLOW
             value: '1'
           - op: "="
             text: RED
diff --git a/nagios/values.yaml b/nagios/values.yaml
index a11df1d58..4bd5b5f59 100644
--- a/nagios/values.yaml
+++ b/nagios/values.yaml
@@ -851,7 +851,7 @@ conf:
       - check_es_cluster_health_status:
           use: generic-service
           service_description: ES_cluster-health-status
-          check_command: check_prom_alert!es_cluster_health_status_alert!CRITICAL- Elasticsearch Cluster is not green. One or more shards or replicas are unallocated!OK- Elasticsearch cluster health is green.
+          check_command: check_prom_alert!es_cluster_health_status_alert!CRITICAL- Elasticsearch cluster health status is not green. One or more shards or replicas are unallocated!OK- Elasticsearch cluster health is green.
           hostgroup_name: prometheus-hosts
       - check_es_cluster_number_nodes_running:
           use: generic-service
diff --git a/prometheus/values.yaml b/prometheus/values.yaml
index 5b00260dd..28ce99e46 100644
--- a/prometheus/values.yaml
+++ b/prometheus/values.yaml
@@ -2038,12 +2038,12 @@ conf:
               description: 'Elasticsearch cluster health status call timedout {{ $value }} times.'
               summary: 'Elasticsearch cluster health status calls are timing out.'
           - alert: es_cluster_health_status_alert
-            expr: elasticsearch_cluster_health_status > 0
+            expr: (sum(elasticsearch_cluster_health_status{color="green"})*2)+sum(elasticsearch_cluster_health_status{color="yellow"}) < 2
             for: 10m
             labels:
               severity: warning
             annotations:
-              description: 'Elasticsearch cluster health status is not green. One or more shards or replicas are unallocated.'
+              description: 'Elasticsearch cluster health status is {{ $value }}, not 2 (green). One or more shards or replicas are unallocated.'
               summary: 'Elasticsearch cluster health status is not green.'
           - alert: es_cluster_health_too_few_nodes_running
             expr: elasticsearch_cluster_health_number_of_nodes < 3
@@ -2061,6 +2061,14 @@ conf:
             annotations:
               description: 'There are only {{$value}} < 3 ElasticSearch data nodes running'
               summary: 'ElasticSearch running on less than 3 data nodes'
+          - alert: es_cluster_health_too_few_data_nodes_running
+            expr: elasticsearch_cluster_health_number_of_data_nodes < 3
+            for: 10m
+            labels:
+              severity: warning
+            annotations:
+              description: 'There are only {{$value}} < 3 ElasticSearch data nodes running'
+              summary: 'ElasticSearch running on less than 3 data nodes'
       mariadb:
         groups:
         - name: mariadb.rules