From 5abf4dee92f0f9047ca2b507976ffbc82a9bafd8 Mon Sep 17 00:00:00 2001
From: Tim Abbott <tabbott@zulipchat.com>
Date: Tue, 6 Nov 2018 16:31:41 -0800
Subject: [PATCH] nagios: Add new host groups for Tornado processes.

We also move all the existing Tornado monitoring rules to the
singletornado_frontends rule.
---
 puppet/zulip_ops/files/nagios3/conf.d/hostgroups.cfg   | 10 ++++++++++
 puppet/zulip_ops/files/nagios3/conf.d/services.cfg     |  4 ++--
 .../zulip_ops/templates/nagios3/hosts.cfg.template.erb |  6 +++---
 3 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/puppet/zulip_ops/files/nagios3/conf.d/hostgroups.cfg b/puppet/zulip_ops/files/nagios3/conf.d/hostgroups.cfg
index 13847e4caf..607df9b756 100644
--- a/puppet/zulip_ops/files/nagios3/conf.d/hostgroups.cfg
+++ b/puppet/zulip_ops/files/nagios3/conf.d/hostgroups.cfg
@@ -35,6 +35,16 @@ define hostgroup {
         alias           Production Frontend Web Servers
         }
 
+define hostgroup {
+        hostgroup_name  multitornado_frontends
+        alias           Frontend Web Servers with multiple Tornado processes
+        }
+
+define hostgroup {
+        hostgroup_name  singletornado_frontends
+        alias           Frontend Web Servers with a single Tornado process
+        }
+
 define hostgroup {
         hostgroup_name    redis
         alias             Redis Servers
diff --git a/puppet/zulip_ops/files/nagios3/conf.d/services.cfg b/puppet/zulip_ops/files/nagios3/conf.d/services.cfg
index f0a2f03a7f..97d8236b8c 100644
--- a/puppet/zulip_ops/files/nagios3/conf.d/services.cfg
+++ b/puppet/zulip_ops/files/nagios3/conf.d/services.cfg
@@ -388,7 +388,7 @@ define service {
         # Workaround weird checks 40s after first error causing alerts
         # from a single failure because cron hasn't run again yet
         max_check_attempts              3
-        hostgroup_name                  frontends
+        hostgroup_name                  singletornado_frontends
         contact_groups                  page_admins
 }
 
@@ -399,7 +399,7 @@ define service {
         # Workaround weird checks 40s after first error causing alerts
         # from a single failure because cron hasn't run again yet
         max_check_attempts              3
-        hostgroup_name                  frontends
+        hostgroup_name                  singletornado_frontends
         contact_groups                  page_admins
 }
 
diff --git a/puppet/zulip_ops/templates/nagios3/hosts.cfg.template.erb b/puppet/zulip_ops/templates/nagios3/hosts.cfg.template.erb
index d40682a102..78e0e6c4a2 100644
--- a/puppet/zulip_ops/templates/nagios3/hosts.cfg.template.erb
+++ b/puppet/zulip_ops/templates/nagios3/hosts.cfg.template.erb
@@ -14,7 +14,7 @@ define host{
        host_name        <%= host %>
        alias            <%= host %>
        address          <%= host %>.<%= @hosts_domain %>
-       hostgroups       all,web,frontends,prod_frontends,pageable_servers
+       hostgroups       all,web,frontends,prod_frontends,singletornado_frontends,pageable_servers
        }
 <% end -%>
 
@@ -24,7 +24,7 @@ define host{
        host_name        <%= host %>
        alias            <%= host %>
        address          <%= host %>
-       hostgroups       all,web,frontends,staging_frontends,not_pageable_servers,postgres,postgres_appdb_primary
+       hostgroups       all,web,frontends,staging_frontends,singletornado_frontends,not_pageable_servers,postgres,postgres_appdb_primary
        }
 <% end -%>
 
@@ -34,7 +34,7 @@ define host{
        host_name        <%= host %>
        alias            <%= host %>
        address          <%= host %>.<%= @hosts_domain %>
-       hostgroups       all,web,frontends,staging_frontends,not_pageable_servers
+       hostgroups       all,web,frontends,staging_frontends,singletornado_frontends,not_pageable_servers
        }
 <% end -%>