From d17364f842a292a4d832437a117efdd30ea3b5c0 Mon Sep 17 00:00:00 2001
From: thomasriley <thomasriley@users.noreply.github.com>
Date: Sat, 27 Jan 2018 14:44:29 +0000
Subject: [PATCH] Adding a new check for checking the number of shards in a
 custer

---
 CHANGELOG.md                        |   2 +
 README.md                           |   1 +
 bin/check-es-maximum-shard-limit.rb | 138 ++++++++++++++++++++++++++++
 3 files changed, 141 insertions(+)
 create mode 100755 bin/check-es-maximum-shard-limit.rb

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 77b67bf..f48edd7 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,6 +4,8 @@ This project adheres to [Semantic Versioning](http://semver.org/).
 This CHANGELOG follows the format listed [here](https://github.com/sensu-plugins/community/blob/master/HOW_WE_CHANGELOG.md)
 
 ## [Unreleased]
+### Added
+- bin/check-es-maximum-shard-limit.rb: added new check for checking the number of shards in the cluster (@thomasriley)
 
 ## [1.8.0] - 2017-11-21
 ### Added
diff --git a/README.md b/README.md
index cc5b5a2..8efe8bb 100644
--- a/README.md
+++ b/README.md
@@ -16,6 +16,7 @@
  * /bin/check-es-heap.rb
  * /bin/check-es-indexes.rb
  * /bin/check-es-indicies-sizes.rb
+ * /bin/check-es-maximum-shard-limit.rb
  * /bin/check-es-node-status.rb
  * /bin/check-es-query-count.rb
  * /bin/check-es-query-exists.rb
diff --git a/bin/check-es-maximum-shard-limit.rb b/bin/check-es-maximum-shard-limit.rb
new file mode 100755
index 0000000..5fc1a46
--- /dev/null
+++ b/bin/check-es-maximum-shard-limit.rb
@@ -0,0 +1,138 @@
+#! /usr/bin/env ruby
+#
+# Checks to see if there are too many shards in the cluster
+# ===
+#
+# DESCRIPTION:
+#   Checks to see if the number of shards in the Elasticsearch cluster
+#   breaches a limit based on the number of nodes in the cluster and
+#   a configurable limit per node
+#
+# OUTPUT:
+#   plain-text
+#
+# PLATFORMS:
+#   Linux
+#
+# DEPENDENCIES:
+#   gem: sensu-plugin
+#   gem: rest-client
+#
+# USAGE:
+#
+# NOTES:
+#   This check will check the limit across the cluster, it does not check the
+#   shard limit on a node by node basis
+#
+# LICENSE:
+#   Thomas Riley
+#   Released under the same terms as Sensu (the MIT license); see LICENSE
+#   for details.
+#
+
+require 'sensu-plugin/check/cli'
+require 'rest-client'
+require 'json'
+require 'base64'
+
+#
+# == Elastic Search Shard Limit Status
+#
+class ESShardMaximumLimit < Sensu::Plugin::Check::CLI
+  option :scheme,
+         description: 'URI scheme',
+         long: '--scheme SCHEME',
+         default: 'http'
+
+  option :server,
+         description: 'Elasticsearch server',
+         short: '-s SERVER',
+         long: '--server SERVER',
+         default: 'localhost'
+
+  option :port,
+         description: 'Port',
+         short: '-p PORT',
+         long: '--port PORT',
+         default: '9200'
+
+  option :allow_non_master,
+         description: 'Allow check to run on non-master nodes',
+         short: '-a',
+         long: '--allow-non-master',
+         default: false
+
+  option :timeout,
+         description: 'Sets the connection timeout for REST client',
+         short: '-t SECS',
+         long: '--timeout SECS',
+         proc: proc(&:to_i),
+         default: 45
+
+  option :node_limit,
+         description: 'Limit of shards per node',
+         short: '-l LIMIT',
+         long: '--limit LIMIT',
+         default: 1000
+
+  option :user,
+         description: 'Elasticsearch User',
+         short: '-u USER',
+         long: '--user USER'
+
+  option :password,
+         description: 'Elasticsearch Password',
+         short: '-P PASS',
+         long: '--password PASS'
+
+  def get_es_resource(resource)
+    headers = {}
+    if config[:user] && config[:password]
+      auth = 'Basic ' + Base64.strict_encode64("#{config[:user]}:#{config[:password]}").chomp
+      headers = { 'Authorization' => auth }
+    end
+
+    r = RestClient::Resource.new("#{config[:scheme]}://#{config[:server]}:#{config[:port]}#{resource}", timeout: config[:timeout], headers: headers)
+    JSON.parse(r.get)
+  rescue Errno::ECONNREFUSED
+    warning 'Connection refused'
+  rescue RestClient::RequestTimeout
+    critical 'Connection timed out'
+  rescue RestClient::ServiceUnavailable
+    critical 'Service is unavailable'
+  rescue Errno::ECONNRESET
+    critical 'Connection reset by peer'
+  end
+
+  def master?
+    state = get_es_resource('/_cluster/state/master_node')
+    local = get_es_resource('/_nodes/_local')
+    local['nodes'].keys.first == state['master_node']
+  end
+
+  def shard_count
+    cluster_health = get_es_resource('/_cluster/health')
+    cluster_health['active_shards']
+  end
+
+  def node_count
+    cluster_health = get_es_resource('/_cluster/health')
+    cluster_health['number_of_nodes']
+  end
+
+  def run
+    if config[:allow_non_master] || master?
+      shard_count = shard_count()
+      node_count = node_count()
+      if shard_count > (node_count * config[:node_limit])
+        critical "Shard count has breached the limit (#{shard_count}/#{node_count * config[:node_limit]})"
+      elsif (shard_count >= (node_count * (config[:node_limit] - 100))) && (shard_count <= (node_count * config[:node_limit]))
+        warning "Shard count is near the limit (#{shard_count}/#{node_count * config[:node_limit]})"
+      elsif shard_count < (node_count * (config[:node_limit] - 100))
+        ok "Shard count is OK (#{shard_count}/#{node_count * config[:node_limit]})"
+      end
+    else
+      ok 'Not the master'
+    end
+  end
+end