summaryrefslogtreecommitdiffstats
path: root/roles
diff options
context:
space:
mode:
Diffstat (limited to 'roles')
-rw-r--r--roles/chrony/README.md31
-rw-r--r--roles/chrony/defaults/main.yml2
-rw-r--r--roles/chrony/handlers/main.yml5
-rw-r--r--roles/chrony/meta/main.yml18
-rw-r--r--roles/chrony/tasks/main.yml30
-rw-r--r--roles/chrony/templates/chrony.conf.j245
-rw-r--r--roles/chrony/vars/main.yml2
-rw-r--r--roles/haproxy/handlers/main.yml1
-rw-r--r--roles/haproxy/tasks/main.yml5
-rw-r--r--roles/lib_timedatectl/library/timedatectl.py74
-rw-r--r--roles/lib_zabbix/library/zbx_action.py147
-rw-r--r--roles/lib_zabbix/tasks/create_template.yml1
-rwxr-xr-xroles/openshift_facts/library/openshift_facts.py9
-rw-r--r--roles/openshift_facts/tasks/main.yml1
-rw-r--r--roles/openshift_master/handlers/main.yml13
-rw-r--r--roles/openshift_master/tasks/main.yml15
-rw-r--r--roles/openshift_node/tasks/main.yml15
-rw-r--r--roles/openshift_node/tasks/storage_plugins/nfs.yml4
-rw-r--r--roles/os_firewall/defaults/main.yml1
-rw-r--r--roles/os_firewall/tasks/main.yml4
-rw-r--r--roles/os_zabbix/tasks/main.yml4
-rw-r--r--roles/os_zabbix/vars/template_docker.yml2
-rw-r--r--roles/oso_monitoring_tools/README.md54
-rw-r--r--roles/oso_monitoring_tools/defaults/main.yml2
-rw-r--r--roles/oso_monitoring_tools/handlers/main.yml2
-rw-r--r--roles/oso_monitoring_tools/meta/main.yml8
-rw-r--r--roles/oso_monitoring_tools/tasks/main.yml18
-rw-r--r--roles/oso_monitoring_tools/vars/main.yml12
28 files changed, 452 insertions, 73 deletions
diff --git a/roles/chrony/README.md b/roles/chrony/README.md
new file mode 100644
index 000000000..bf15d9669
--- /dev/null
+++ b/roles/chrony/README.md
@@ -0,0 +1,31 @@
+Role Name
+=========
+
+A role to configure chrony as the ntp client
+
+Requirements
+------------
+
+
+Role Variables
+--------------
+
+chrony_ntp_servers: a list of ntp servers to use the chrony.conf file
+
+Dependencies
+------------
+
+roles/lib_timedatectl
+
+Example Playbook
+----------------
+
+License
+-------
+
+Apache 2.0
+
+Author Information
+------------------
+
+Openshift Operations
diff --git a/roles/chrony/defaults/main.yml b/roles/chrony/defaults/main.yml
new file mode 100644
index 000000000..95576e666
--- /dev/null
+++ b/roles/chrony/defaults/main.yml
@@ -0,0 +1,2 @@
+---
+# defaults file for chrony
diff --git a/roles/chrony/handlers/main.yml b/roles/chrony/handlers/main.yml
new file mode 100644
index 000000000..1973c79e2
--- /dev/null
+++ b/roles/chrony/handlers/main.yml
@@ -0,0 +1,5 @@
+---
+- name: Restart chronyd
+ service:
+ name: chronyd
+ state: restarted
diff --git a/roles/chrony/meta/main.yml b/roles/chrony/meta/main.yml
new file mode 100644
index 000000000..85595d7c3
--- /dev/null
+++ b/roles/chrony/meta/main.yml
@@ -0,0 +1,18 @@
+---
+galaxy_info:
+ author: Openshift Operations
+ description: Configure chrony as an ntp server
+ company: Red Hat
+ license: Apache 2.0
+ min_ansible_version: 1.9.2
+ platforms:
+ - name: EL
+ versions:
+ - 7
+ - name: Fedora
+ versions:
+ - all
+ categories:
+ - system
+dependencies:
+- roles/lib_timedatectl
diff --git a/roles/chrony/tasks/main.yml b/roles/chrony/tasks/main.yml
new file mode 100644
index 000000000..fae6d8e4c
--- /dev/null
+++ b/roles/chrony/tasks/main.yml
@@ -0,0 +1,30 @@
+---
+- name: remove ntp package
+ yum:
+ name: ntp
+ state: absent
+
+- name: ensure chrony package is installed
+ yum:
+ name: chrony
+ state: installed
+
+- name: Install /etc/chrony.conf
+ template:
+ src: chrony.conf.j2
+ dest: /etc/chrony.conf
+ owner: root
+ group: root
+ mode: 0644
+ notify:
+ - Restart chronyd
+
+- name: enabled timedatectl set-ntp yes
+ timedatectl:
+ ntp: True
+
+- name:
+ service:
+ name: chronyd
+ state: started
+ enabled: yes
diff --git a/roles/chrony/templates/chrony.conf.j2 b/roles/chrony/templates/chrony.conf.j2
new file mode 100644
index 000000000..de43b6364
--- /dev/null
+++ b/roles/chrony/templates/chrony.conf.j2
@@ -0,0 +1,45 @@
+# Use public servers from the pool.ntp.org project.
+# Please consider joining the pool (http://www.pool.ntp.org/join.html).
+{% for server in chrony_ntp_servers %}
+server {{ server }} iburst
+{% endfor %}
+
+# Ignore stratum in source selection.
+stratumweight 0
+
+# Record the rate at which the system clock gains/losses time.
+driftfile /var/lib/chrony/drift
+
+# Enable kernel RTC synchronization.
+rtcsync
+
+# In first three updates step the system clock instead of slew
+# if the adjustment is larger than 10 seconds.
+makestep 10 3
+
+# Allow NTP client access from local network.
+#allow 192.168/16
+
+# Listen for commands only on localhost.
+bindcmdaddress 127.0.0.1
+bindcmdaddress ::1
+
+# Serve time even if not synchronized to any NTP server.
+#local stratum 10
+
+keyfile /etc/chrony.keys
+
+# Specify the key used as password for chronyc.
+commandkey 1
+
+# Generate command key if missing.
+generatecommandkey
+
+# Disable logging of client accesses.
+noclientlog
+
+# Send a message to syslog if a clock adjustment is larger than 0.5 seconds.
+logchange 0.5
+
+logdir /var/log/chrony
+#log measurements statistics tracking
diff --git a/roles/chrony/vars/main.yml b/roles/chrony/vars/main.yml
new file mode 100644
index 000000000..061a21547
--- /dev/null
+++ b/roles/chrony/vars/main.yml
@@ -0,0 +1,2 @@
+---
+# vars file for chrony
diff --git a/roles/haproxy/handlers/main.yml b/roles/haproxy/handlers/main.yml
index ee60adcab..5b8691b26 100644
--- a/roles/haproxy/handlers/main.yml
+++ b/roles/haproxy/handlers/main.yml
@@ -3,3 +3,4 @@
service:
name: haproxy
state: restarted
+ when: not (haproxy_start_result_changed | default(false) | bool)
diff --git a/roles/haproxy/tasks/main.yml b/roles/haproxy/tasks/main.yml
index 97f870829..0b8370ce2 100644
--- a/roles/haproxy/tasks/main.yml
+++ b/roles/haproxy/tasks/main.yml
@@ -19,6 +19,5 @@
enabled: yes
register: start_result
-- name: Pause 30 seconds if haproxy was just started
- pause: seconds=30
- when: start_result | changed
+- set_fact:
+ haproxy_start_result_changed: "{{ start_result | changed }}"
diff --git a/roles/lib_timedatectl/library/timedatectl.py b/roles/lib_timedatectl/library/timedatectl.py
new file mode 100644
index 000000000..b6eab5918
--- /dev/null
+++ b/roles/lib_timedatectl/library/timedatectl.py
@@ -0,0 +1,74 @@
+#!/usr/bin/env python
+'''
+ timedatectl ansible module
+
+ This module supports setting ntp enabled
+'''
+import subprocess
+
+
+
+
+def do_timedatectl(options=None):
+ ''' subprocess timedatectl '''
+
+ cmd = ['/usr/bin/timedatectl']
+ if options:
+ cmd += options.split()
+
+ proc = subprocess.Popen(cmd, stdin=None, stdout=subprocess.PIPE)
+ proc.wait()
+ return proc.stdout.read()
+
+def main():
+ ''' Ansible module for timedatectl
+ '''
+
+ module = AnsibleModule(
+ argument_spec=dict(
+ #state=dict(default='enabled', type='str'),
+ ntp=dict(default=True, type='bool'),
+ ),
+ #supports_check_mode=True
+ )
+
+ # do something
+ ntp_enabled = False
+
+ results = do_timedatectl()
+
+ for line in results.split('\n'):
+ if 'NTP enabled' in line:
+ if 'yes' in line:
+ ntp_enabled = True
+
+ ########
+ # Enable NTP
+ ########
+ if module.params['ntp']:
+ if ntp_enabled:
+ module.exit_json(changed=False, results="enabled", state="enabled")
+
+ # Enable it
+ # Commands to enable ntp
+ else:
+ results = do_timedatectl('set-ntp yes')
+ module.exit_json(changed=True, results="enabled", state="enabled", cmdout=results)
+
+ #########
+ # Disable NTP
+ #########
+ else:
+ if not ntp_enabled:
+ module.exit_json(changed=False, results="disabled", state="disabled")
+
+ results = do_timedatectl('set-ntp no')
+ module.exit_json(changed=True, results="disabled", state="disabled")
+
+ module.exit_json(failed=True, changed=False, results="Something went wrong", state="unknown")
+
+# Pylint is getting in the way of basic Ansible
+# pylint: disable=redefined-builtin,wildcard-import,unused-wildcard-import
+from ansible.module_utils.basic import *
+
+main()
diff --git a/roles/lib_zabbix/library/zbx_action.py b/roles/lib_zabbix/library/zbx_action.py
index c08bef4f7..2f9524556 100644
--- a/roles/lib_zabbix/library/zbx_action.py
+++ b/roles/lib_zabbix/library/zbx_action.py
@@ -81,6 +81,61 @@ def filter_differences(zabbix_filters, user_filters):
return rval
+def opconditions_diff(zab_val, user_val):
+ ''' Report whether there are differences between opconditions on
+ zabbix and opconditions supplied by user '''
+
+ if len(zab_val) != len(user_val):
+ return True
+
+ for z_cond, u_cond in zip(zab_val, user_val):
+ if not all([str(u_cond[op_key]) == z_cond[op_key] for op_key in \
+ ['conditiontype', 'operator', 'value']]):
+ return True
+
+ return False
+
+def opmessage_diff(zab_val, user_val):
+ ''' Report whether there are differences between opmessage on
+ zabbix and opmessage supplied by user '''
+
+ for op_msg_key, op_msg_val in user_val.items():
+ if zab_val[op_msg_key] != str(op_msg_val):
+ return True
+
+ return False
+
+def opmessage_grp_diff(zab_val, user_val):
+ ''' Report whether there are differences between opmessage_grp
+ on zabbix and opmessage_grp supplied by user '''
+
+ zab_grp_ids = set([ugrp['usrgrpid'] for ugrp in zab_val])
+ usr_grp_ids = set([ugrp['usrgrpid'] for ugrp in user_val])
+ if usr_grp_ids != zab_grp_ids:
+ return True
+
+ return False
+
+def opmessage_usr_diff(zab_val, user_val):
+ ''' Report whether there are differences between opmessage_usr
+ on zabbix and opmessage_usr supplied by user '''
+
+ zab_usr_ids = set([usr['usrid'] for usr in zab_val])
+ usr_ids = set([usr['usrid'] for usr in user_val])
+ if usr_ids != zab_usr_ids:
+ return True
+
+ return False
+
+def opcommand_diff(zab_op_cmd, usr_op_cmd):
+ ''' Check whether user-provided opcommand matches what's already
+ stored in Zabbix '''
+
+ for usr_op_cmd_key, usr_op_cmd_val in usr_op_cmd.items():
+ if zab_op_cmd[usr_op_cmd_key] != str(usr_op_cmd_val):
+ return True
+ return False
+
def host_in_zabbix(zab_hosts, usr_host):
''' Check whether a particular user host is already in the
Zabbix list of hosts '''
@@ -106,23 +161,11 @@ def hostlist_in_zabbix(zab_hosts, usr_hosts):
return True
-def opcommand_diff(zab_op_cmd, usr_op_cmd):
- ''' Check whether user-provided opcommand matches what's already
- stored in Zabbix '''
-
- for usr_op_cmd_key, usr_op_cmd_val in usr_op_cmd.items():
- if zab_op_cmd[usr_op_cmd_key] != str(usr_op_cmd_val):
- return True
- return False
-
-# This logic is quite complex. We are comparing two lists of dictionaries.
-# The outer for-loops allow us to descend down into both lists at the same time
-# and then walk over the key,val pairs of the incoming user dict's changes
-# or updates. The if-statements are looking at different sub-object types and
-# comparing them. The other suggestion on how to write this is to write a recursive
-# compare function but for the time constraints and for complexity I decided to go
-# this route.
-# pylint: disable=too-many-branches
+# We are comparing two lists of dictionaries (the one stored on zabbix and the
+# one the user is providing). For each type of operation, determine whether there
+# is a difference between what is stored on zabbix and what the user is providing.
+# If there is a difference, we take the user-provided data for what needs to
+# be stored/updated into zabbix.
def operation_differences(zabbix_ops, user_ops):
'''Determine the differences from user and zabbix for operations'''
@@ -132,49 +175,41 @@ def operation_differences(zabbix_ops, user_ops):
rval = {}
for zab, user in zip(zabbix_ops, user_ops):
- for key, val in user.items():
- if key == 'opconditions':
- if len(zab[key]) != len(val):
- rval[key] = val
- break
- for z_cond, u_cond in zip(zab[key], user[key]):
- if not all([str(u_cond[op_key]) == z_cond[op_key] for op_key in \
- ['conditiontype', 'operator', 'value']]):
- rval[key] = val
- break
- elif key == 'opmessage':
- # Verify each passed param matches
- for op_msg_key, op_msg_val in val.items():
- if zab[key][op_msg_key] != str(op_msg_val):
- rval[key] = val
- break
-
- elif key == 'opmessage_grp':
- zab_grp_ids = set([ugrp['usrgrpid'] for ugrp in zab[key]])
- usr_grp_ids = set([ugrp['usrgrpid'] for ugrp in val])
- if usr_grp_ids != zab_grp_ids:
- rval[key] = val
-
- elif key == 'opmessage_usr':
- zab_usr_ids = set([usr['userid'] for usr in zab[key]])
- usr_ids = set([usr['userid'] for usr in val])
- if usr_ids != zab_usr_ids:
- rval[key] = val
-
- elif key == 'opcommand':
- if opcommand_diff(zab[key], val):
- rval[key] = val
- break
+ for oper in user.keys():
+ if oper == 'opconditions' and opconditions_diff(zab[oper], \
+ user[oper]):
+ rval[oper] = user[oper]
+
+ elif oper == 'opmessage' and opmessage_diff(zab[oper], \
+ user[oper]):
+ rval[oper] = user[oper]
+
+ elif oper == 'opmessage_grp' and opmessage_grp_diff(zab[oper], \
+ user[oper]):
+ rval[oper] = user[oper]
+
+ elif oper == 'opmessage_usr' and opmessage_usr_diff(zab[oper], \
+ user[oper]):
+ rval[oper] = user[oper]
+
+ elif oper == 'opcommand' and opcommand_diff(zab[oper], \
+ user[oper]):
+ rval[oper] = user[oper]
# opcommand_grp can be treated just like opcommand_hst
# as opcommand_grp[] is just a list of groups
- elif key == 'opcommand_hst' or key == 'opcommand_grp':
- if not hostlist_in_zabbix(zab[key], val):
- rval[key] = val
- break
+ elif oper == 'opcommand_hst' or oper == 'opcommand_grp':
+ if not hostlist_in_zabbix(zab[oper], user[oper]):
+ rval[oper] = user[oper]
+
+ # if it's any other type of operation than the ones tested above
+ # just do a direct compare
+ elif oper not in ['opconditions', 'opmessage', 'opmessage_grp',
+ 'opmessage_usr', 'opcommand', 'opcommand_hst',
+ 'opcommand_grp'] \
+ and str(zab[oper]) != str(user[oper]):
+ rval[oper] = user[oper]
- elif zab[key] != str(val):
- rval[key] = val
return rval
def get_users(zapi, users):
diff --git a/roles/lib_zabbix/tasks/create_template.yml b/roles/lib_zabbix/tasks/create_template.yml
index 47749389e..61344357a 100644
--- a/roles/lib_zabbix/tasks/create_template.yml
+++ b/roles/lib_zabbix/tasks/create_template.yml
@@ -57,6 +57,7 @@
expression: "{{ item.expression }}"
priority: "{{ item.priority }}"
url: "{{ item.url | default(None, True) }}"
+ status: "{{ item.status | default('', True) }}"
with_items: template.ztriggers
when: template.ztriggers is defined
diff --git a/roles/openshift_facts/library/openshift_facts.py b/roles/openshift_facts/library/openshift_facts.py
index 9096f7ebf..0820989af 100755
--- a/roles/openshift_facts/library/openshift_facts.py
+++ b/roles/openshift_facts/library/openshift_facts.py
@@ -188,9 +188,6 @@ def normalize_gce_facts(metadata, facts):
_, _, zone = metadata['instance']['zone'].rpartition('/')
facts['zone'] = zone
- # Default to no sdn for GCE deployments
- facts['use_openshift_sdn'] = False
-
# GCE currently only supports a single interface
facts['network']['ip'] = facts['network']['interfaces'][0]['ips'][0]
pub_ip = facts['network']['interfaces'][0]['public_ips'][0]
@@ -900,10 +897,6 @@ def apply_provider_facts(facts, provider_facts):
if not provider_facts:
return facts
- use_openshift_sdn = provider_facts.get('use_openshift_sdn')
- if isinstance(use_openshift_sdn, bool):
- facts['common']['use_openshift_sdn'] = use_openshift_sdn
-
common_vars = [('hostname', 'ip'), ('public_hostname', 'public_ip')]
for h_var, ip_var in common_vars:
ip_value = provider_facts['network'].get(ip_var)
@@ -1094,7 +1087,7 @@ class OpenShiftFacts(object):
Raises:
OpenShiftFactsUnsupportedRoleError:
"""
- known_roles = ['common', 'master', 'node', 'master_sdn', 'node_sdn', 'etcd', 'nfs']
+ known_roles = ['common', 'master', 'node', 'etcd', 'nfs']
def __init__(self, role, filename, local_facts, additive_facts_to_overwrite=False):
self.changed = False
diff --git a/roles/openshift_facts/tasks/main.yml b/roles/openshift_facts/tasks/main.yml
index 87fa99a3b..e40a1b329 100644
--- a/roles/openshift_facts/tasks/main.yml
+++ b/roles/openshift_facts/tasks/main.yml
@@ -10,6 +10,7 @@
shell: ls /run/ostree-booted
ignore_errors: yes
failed_when: false
+ changed_when: false
register: ostree_output
# Locally setup containerized facts for now
diff --git a/roles/openshift_master/handlers/main.yml b/roles/openshift_master/handlers/main.yml
index e1b95eda4..6b9992eea 100644
--- a/roles/openshift_master/handlers/main.yml
+++ b/roles/openshift_master/handlers/main.yml
@@ -2,11 +2,24 @@
- name: restart master
service: name={{ openshift.common.service_type }}-master state=restarted
when: (not openshift_master_ha | bool) and (not (master_service_status_changed | default(false) | bool))
+ notify: Verify API Server
- name: restart master api
service: name={{ openshift.common.service_type }}-master-api state=restarted
when: (openshift_master_ha | bool) and (not (master_api_service_status_changed | default(false) | bool)) and openshift.master.cluster_method == 'native'
+ notify: Verify API Server
- name: restart master controllers
service: name={{ openshift.common.service_type }}-master-controllers state=restarted
when: (openshift_master_ha | bool) and (not (master_controllers_service_status_changed | default(false) | bool)) and openshift.master.cluster_method == 'native'
+
+- name: Verify API Server
+ # Using curl here since the uri module requires python-httplib2 and
+ # wait_for port doesn't provide health information.
+ command: >
+ curl -k --head --silent {{ openshift.master.api_url }}
+ register: api_available_output
+ until: api_available_output.stdout.find("200 OK") != -1
+ retries: 120
+ delay: 1
+ changed_when: false
diff --git a/roles/openshift_master/tasks/main.yml b/roles/openshift_master/tasks/main.yml
index 462a7ab58..44e7e3178 100644
--- a/roles/openshift_master/tasks/main.yml
+++ b/roles/openshift_master/tasks/main.yml
@@ -269,6 +269,7 @@
service: name={{ openshift.common.service_type }}-master enabled=yes state=started
when: not openshift_master_ha | bool
register: start_result
+ notify: Verify API Server
- name: Stop and disable non HA master when running HA
service: name={{ openshift.common.service_type }}-master enabled=no state=stopped
@@ -287,6 +288,20 @@
master_api_service_status_changed: "{{ start_result | changed }}"
when: openshift_master_ha | bool and openshift.master.cluster_method == 'native'
+# A separate wait is required here for native HA since notifies will
+# be resolved after all tasks in the role.
+- name: Wait for API to become available
+ # Using curl here since the uri module requires python-httplib2 and
+ # wait_for port doesn't provide health information.
+ command: >
+ curl -k --head --silent {{ openshift.master.api_url }}
+ register: api_available_output
+ until: api_available_output.stdout.find("200 OK") != -1
+ retries: 120
+ delay: 1
+ changed_when: false
+ when: openshift_master_ha | bool and openshift.master.cluster_method == 'native' and master_api_service_status_changed | bool
+
- name: Start and enable master controller
service: name={{ openshift.common.service_type }}-master-controllers enabled=yes state=started
when: openshift_master_ha | bool and openshift.master.cluster_method == 'native'
diff --git a/roles/openshift_node/tasks/main.yml b/roles/openshift_node/tasks/main.yml
index 0828d8e2c..9035248f9 100644
--- a/roles/openshift_node/tasks/main.yml
+++ b/roles/openshift_node/tasks/main.yml
@@ -103,6 +103,21 @@
- name: Additional storage plugin configuration
include: storage_plugins/main.yml
+# Necessary because when you're on a node that's also a master the master will be
+# restarted after the node restarts docker and it will take up to 60 seconds for
+# systemd to start the master again
+- name: Wait for master API to become available before proceeding
+ # Using curl here since the uri module requires python-httplib2 and
+ # wait_for port doesn't provide health information.
+ command: >
+ curl -k --head --silent {{ openshift_node_master_api_url }}
+ register: api_available_output
+ until: api_available_output.stdout.find("200 OK") != -1
+ retries: 120
+ delay: 1
+ changed_when: false
+ when: openshift.common.is_containerized | bool
+
- name: Start and enable node
service: name={{ openshift.common.service_type }}-node enabled=yes state=started
register: start_result
diff --git a/roles/openshift_node/tasks/storage_plugins/nfs.yml b/roles/openshift_node/tasks/storage_plugins/nfs.yml
index 1edf21d9b..14a613786 100644
--- a/roles/openshift_node/tasks/storage_plugins/nfs.yml
+++ b/roles/openshift_node/tasks/storage_plugins/nfs.yml
@@ -1,4 +1,8 @@
---
+- name: Install NFS storage plugin dependencies
+ action: "{{ ansible_pkg_mgr }} name=nfs-utils state=present"
+ when: not openshift.common.is_atomic | bool
+
- name: Set seboolean to allow nfs storage plugin access from containers
seboolean:
name: virt_use_nfs
diff --git a/roles/os_firewall/defaults/main.yml b/roles/os_firewall/defaults/main.yml
index bcf1d9a34..e3176e611 100644
--- a/roles/os_firewall/defaults/main.yml
+++ b/roles/os_firewall/defaults/main.yml
@@ -1,2 +1,3 @@
---
+os_firewall_enabled: True
os_firewall_use_firewalld: True
diff --git a/roles/os_firewall/tasks/main.yml b/roles/os_firewall/tasks/main.yml
index ad89ef97c..076e5e311 100644
--- a/roles/os_firewall/tasks/main.yml
+++ b/roles/os_firewall/tasks/main.yml
@@ -1,6 +1,6 @@
---
- include: firewall/firewalld.yml
- when: os_firewall_use_firewalld
+ when: os_firewall_enabled | bool and os_firewall_use_firewalld | bool
- include: firewall/iptables.yml
- when: not os_firewall_use_firewalld
+ when: os_firewall_enabled | bool and not os_firewall_use_firewalld | bool
diff --git a/roles/os_zabbix/tasks/main.yml b/roles/os_zabbix/tasks/main.yml
index a8b65dd56..7552086d4 100644
--- a/roles/os_zabbix/tasks/main.yml
+++ b/roles/os_zabbix/tasks/main.yml
@@ -1,8 +1,4 @@
---
-- fail:
- msg: "Zabbix config is not yet supported on atomic hosts"
- when: openshift.common.is_containerized | bool
-
- name: Main List all templates
zbx_template:
zbx_server: "{{ ozb_server }}"
diff --git a/roles/os_zabbix/vars/template_docker.yml b/roles/os_zabbix/vars/template_docker.yml
index a05e552e3..dd13e76f7 100644
--- a/roles/os_zabbix/vars/template_docker.yml
+++ b/roles/os_zabbix/vars/template_docker.yml
@@ -72,10 +72,12 @@ g_template_docker:
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_docker_ping.asciidoc'
priority: high
+ # Re-enable for OpenShift 3.1.1 (https://bugzilla.redhat.com/show_bug.cgi?id=1292971#c6)
- name: 'docker.container.dns.resolution failed on {HOST.NAME}'
expression: '{Template Docker:docker.container.dns.resolution.min(#3)}>0'
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_docker_dns.asciidoc'
priority: average
+ status: disabled
- name: 'docker.container.existing.dns.resolution.failed on {HOST.NAME}'
expression: '{Template Docker:docker.container.existing.dns.resolution.failed.min(#3)}>0'
diff --git a/roles/oso_monitoring_tools/README.md b/roles/oso_monitoring_tools/README.md
new file mode 100644
index 000000000..4215f9eeb
--- /dev/null
+++ b/roles/oso_monitoring_tools/README.md
@@ -0,0 +1,54 @@
+Role Name
+=========
+
+This role will install the Openshift Monitoring Utilities
+
+Requirements
+------------
+
+Any pre-requisites that may not be covered by Ansible itself or the role should be mentioned here. For instance, if the role uses the EC2 module, it may be a good idea to mention in this section that the boto package is required.
+
+Role Variables
+--------------
+
+osomt_zagg_client_config
+
+from vars/main.yml:
+
+osomt_zagg_client_config:
+ host:
+ name: "{{ osomt_host_name }}"
+ zagg:
+ url: "{{ osomt_zagg_url }}"
+ user: "{{ osomt_zagg_user }}"
+ pass: "{{ osomt_zagg_password }}"
+ ssl_verify: "{{ osomt_zagg_ssl_verify }}"
+ verbose: "{{ osomt_zagg_verbose }}"
+ debug: "{{ osomt_zagg_debug }}"
+
+Dependencies
+------------
+
+None
+
+Example Playbook
+----------------
+
+- role: "oso_monitoring_tools"
+ osomt_host_name: hostname
+ osomt_zagg_url: http://path.to/zagg_web
+ osomt_zagg_user: admin
+ osomt_zagg_password: password
+ osomt_zagg_ssl_verify: True
+ osomt_zagg_verbose: False
+ osomt_zagg_debug: False
+
+License
+-------
+
+BSD
+
+Author Information
+------------------
+
+Openshift Operations
diff --git a/roles/oso_monitoring_tools/defaults/main.yml b/roles/oso_monitoring_tools/defaults/main.yml
new file mode 100644
index 000000000..a17424f25
--- /dev/null
+++ b/roles/oso_monitoring_tools/defaults/main.yml
@@ -0,0 +1,2 @@
+---
+# defaults file for oso_monitoring_tools
diff --git a/roles/oso_monitoring_tools/handlers/main.yml b/roles/oso_monitoring_tools/handlers/main.yml
new file mode 100644
index 000000000..cefa780ab
--- /dev/null
+++ b/roles/oso_monitoring_tools/handlers/main.yml
@@ -0,0 +1,2 @@
+---
+# handlers file for oso_monitoring_tools
diff --git a/roles/oso_monitoring_tools/meta/main.yml b/roles/oso_monitoring_tools/meta/main.yml
new file mode 100644
index 000000000..9c42b68dc
--- /dev/null
+++ b/roles/oso_monitoring_tools/meta/main.yml
@@ -0,0 +1,8 @@
+---
+galaxy_info:
+ author: OpenShift Operations
+ description: Install Openshift Monitoring tools
+ company: Red Hat, Inc
+ license: ASL 2.0
+ min_ansible_version: 1.2
+dependencies: []
diff --git a/roles/oso_monitoring_tools/tasks/main.yml b/roles/oso_monitoring_tools/tasks/main.yml
new file mode 100644
index 000000000..c90fc56e2
--- /dev/null
+++ b/roles/oso_monitoring_tools/tasks/main.yml
@@ -0,0 +1,18 @@
+---
+# tasks file for oso_monitoring_tools
+- name: Install the Openshift Tools RPMS
+ yum:
+ name: "{{ item }}"
+ state: latest
+ with_items:
+ - openshift-tools-scripts-monitoring-zagg-client
+ - python-openshift-tools-monitoring-zagg
+ - python-openshift-tools-monitoring-zabbix
+
+- debug: var=g_zagg_client_config
+
+- name: Generate the /etc/openshift_tools/zagg_client.yaml config file
+ copy:
+ content: "{{ osomt_zagg_client_config | to_nice_yaml }}"
+ dest: /etc/openshift_tools/zagg_client.yaml
+ mode: "644"
diff --git a/roles/oso_monitoring_tools/vars/main.yml b/roles/oso_monitoring_tools/vars/main.yml
new file mode 100644
index 000000000..3538ba30b
--- /dev/null
+++ b/roles/oso_monitoring_tools/vars/main.yml
@@ -0,0 +1,12 @@
+---
+# vars file for oso_monitoring_tools
+osomt_zagg_client_config:
+ host:
+ name: "{{ osomt_host_name }}"
+ zagg:
+ url: "{{ osomt_zagg_url }}"
+ user: "{{ osomt_zagg_user }}"
+ pass: "{{ osomt_zagg_password }}"
+ ssl_verify: "{{ osomt_zagg_ssl_verify }}"
+ verbose: "{{ osomt_zagg_verbose }}"
+ debug: "{{ osomt_zagg_debug }}"