summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--README_AWS.md22
-rw-r--r--README_GCE.md17
-rw-r--r--README_OSE.md17
-rw-r--r--README_libvirt.md12
-rw-r--r--README_origin.md18
-rwxr-xr-xbin/cluster56
-rwxr-xr-xinventory/gce/hosts/gce.py9
-rwxr-xr-xinventory/openstack/hosts/nova.py2
-rw-r--r--playbooks/adhoc/docker_loopback_to_lvm/docker-storage-setup2
-rw-r--r--playbooks/adhoc/docker_loopback_to_lvm/docker_loopback_to_direct_lvm.yml142
-rwxr-xr-xplaybooks/adhoc/docker_loopback_to_lvm/ops-docker-loopback-to-direct-lvm.yml104
-rw-r--r--playbooks/adhoc/docker_storage_cleanup/docker_storage_cleanup.yml69
-rw-r--r--playbooks/adhoc/grow_docker_vg/filter_plugins/oo_filters.py41
-rw-r--r--playbooks/adhoc/grow_docker_vg/grow_docker_vg.yml206
-rw-r--r--playbooks/adhoc/s3_registry/s3_registry.j220
-rw-r--r--playbooks/adhoc/s3_registry/s3_registry.yml61
-rw-r--r--playbooks/adhoc/upgrades/README.md21
l---------playbooks/adhoc/upgrades/filter_plugins1
l---------playbooks/adhoc/upgrades/lookup_plugins1
l---------playbooks/adhoc/upgrades/roles1
-rw-r--r--playbooks/adhoc/upgrades/upgrade.yml115
-rw-r--r--playbooks/aws/openshift-cluster/tasks/launch_instances.yml1
-rw-r--r--playbooks/gce/openshift-cluster/config.yml5
-rw-r--r--playbooks/gce/openshift-cluster/join_node.yml49
-rw-r--r--playbooks/gce/openshift-cluster/launch.yml33
-rw-r--r--playbooks/gce/openshift-cluster/list.yml4
-rw-r--r--playbooks/gce/openshift-cluster/tasks/launch_instances.yml32
-rw-r--r--playbooks/gce/openshift-cluster/terminate.yml55
-rw-r--r--playbooks/gce/openshift-cluster/vars.yml8
-rw-r--r--playbooks/libvirt/openshift-cluster/tasks/launch_instances.yml2
-rw-r--r--playbooks/libvirt/openshift-cluster/templates/network.xml2
-rw-r--r--playbooks/libvirt/openshift-cluster/templates/user-data2
-rw-r--r--roles/ansible_tower/tasks/main.yaml3
-rw-r--r--roles/etcd/tasks/main.yml1
-rw-r--r--roles/etcd_ca/tasks/main.yml1
-rw-r--r--roles/fluentd_master/tasks/main.yml1
-rw-r--r--roles/lib_zabbix/library/zbx_action.py538
-rw-r--r--roles/lib_zabbix/library/zbx_discoveryrule.py36
-rw-r--r--roles/lib_zabbix/library/zbx_item.py2
-rw-r--r--roles/lib_zabbix/library/zbx_itemprototype.py67
-rw-r--r--roles/lib_zabbix/library/zbx_trigger.py42
-rw-r--r--roles/lib_zabbix/library/zbx_triggerprototype.py177
-rw-r--r--roles/lib_zabbix/library/zbx_user_media.py56
-rw-r--r--roles/lib_zabbix/tasks/create_template.yml50
-rw-r--r--roles/openshift_examples/defaults/main.yml2
-rw-r--r--roles/openshift_examples/files/examples/xpaas-templates/eap6-https-sti.json4
-rw-r--r--roles/openshift_examples/tasks/main.yml12
-rwxr-xr-xroles/openshift_facts/library/openshift_facts.py35
-rw-r--r--roles/openshift_facts/tasks/main.yml2
-rw-r--r--roles/openshift_manage_node/tasks/main.yml8
-rw-r--r--roles/openshift_master/tasks/main.yml2
-rw-r--r--roles/openshift_master/templates/master.yaml.v1.j22
-rw-r--r--roles/openshift_master/templates/scheduler.json.j22
-rw-r--r--roles/openshift_master/templates/v1_partials/oauthConfig.j21
-rw-r--r--roles/openshift_node/tasks/main.yml3
-rw-r--r--roles/openshift_node/templates/node.yaml.v1.j26
-rw-r--r--roles/openshift_serviceaccounts/tasks/main.yml2
-rw-r--r--roles/os_zabbix/tasks/main.yml36
-rw-r--r--roles/os_zabbix/vars/template_app_zabbix_agent.yml23
-rw-r--r--roles/os_zabbix/vars/template_app_zabbix_server.yml408
-rw-r--r--roles/os_zabbix/vars/template_openshift_master.yml45
-rw-r--r--roles/os_zabbix/vars/template_openshift_node.yml44
-rw-r--r--roles/os_zabbix/vars/template_ops_tools.yml23
-rw-r--r--roles/os_zabbix/vars/template_os_linux.yml80
64 files changed, 2627 insertions, 217 deletions
diff --git a/README_AWS.md b/README_AWS.md
index c511741b9..3a5790eb3 100644
--- a/README_AWS.md
+++ b/README_AWS.md
@@ -154,18 +154,10 @@ Note: If no deployment type is specified, then the default is origin.
## Post-ansible steps
-Create the default router
--------------------------
-On the master host:
-```sh
-oadm router --create=true \
- --credentials=/etc/openshift/master/openshift-router.kubeconfig
-```
-
-Create the default docker-registry
-----------------------------------
-On the master host:
-```sh
-oadm registry --create=true \
- --credentials=/etc/openshift/master/openshift-registry.kubeconfig
-``` \ No newline at end of file
+
+You should now be ready to follow the **What's Next?** section of the advanced installation guide to deploy your router, registry, and other components.
+
+Refer to the advanced installation guide for your deployment type:
+
+* [OpenShift Enterprise](https://docs.openshift.com/enterprise/3.0/install_config/install/advanced_install.html#what-s-next)
+* [OpenShift Origin](https://docs.openshift.org/latest/install_config/install/advanced_install.html#what-s-next)
diff --git a/README_GCE.md b/README_GCE.md
index f6c5138c1..50f8ade70 100644
--- a/README_GCE.md
+++ b/README_GCE.md
@@ -39,6 +39,13 @@ Create a gce.ini file for GCE
* gce_service_account_pem_file_path - Full path from previous steps
* gce_project_id - Found in "Projects", it list all the gce projects you are associated with. The page lists their "Project Name" and "Project ID". You want the "Project ID"
+Mandatory customization variables (check the values according to your tenant):
+* zone = europe-west1-d
+* network = default
+* gce_machine_type = n1-standard-2
+* gce_machine_image = preinstalled-slave-50g-v5
+
+
1. vi ~/.gce/gce.ini
1. make the contents look like this:
```
@@ -46,11 +53,15 @@ Create a gce.ini file for GCE
gce_service_account_email_address = long...@developer.gserviceaccount.com
gce_service_account_pem_file_path = /full/path/to/project_id-gce_key_hash.pem
gce_project_id = project_id
+zone = europe-west1-d
+network = default
+gce_machine_type = n1-standard-2
+gce_machine_image = preinstalled-slave-50g-v5
+
```
-1. Setup a sym link so that gce.py will pick it up (link must be in same dir as gce.py)
+1. Define the environment variable GCE_INI_PATH so gce.py can pick it up and bin/cluster can also read it
```
- cd openshift-ansible/inventory/gce
- ln -s ~/.gce/gce.ini gce.ini
+export GCE_INI_PATH=~/.gce/gce.ini
```
diff --git a/README_OSE.md b/README_OSE.md
index cce1ec030..79ad07044 100644
--- a/README_OSE.md
+++ b/README_OSE.md
@@ -101,6 +101,7 @@ ose3-master.example.com
# host group for nodes
[nodes]
+ose3-master.example.com
ose3-node[1:2].example.com
```
@@ -116,22 +117,8 @@ ansible-playbook playbooks/byo/config.yml
inventory file use the -i option for ansible-playbook.
## Post-ansible steps
-#### Create the default router
-On the master host:
-```sh
-oadm router --create=true \
- --credentials=/etc/openshift/master/openshift-router.kubeconfig \
- --images='rcm-img-docker01.build.eng.bos.redhat.com:5001/openshift3/ose-${component}:${version}'
-```
-#### Create the default docker-registry
-On the master host:
-```sh
-oadm registry --create=true \
- --credentials=/etc/openshift/master/openshift-registry.kubeconfig \
- --images='rcm-img-docker01.build.eng.bos.redhat.com:5001/openshift3/ose-${component}:${version}' \
- --mount-host=/var/lib/openshift/docker-registry
-```
+You should now be ready to follow the [What's Next?](https://docs.openshift.com/enterprise/3.0/install_config/install/advanced_install.html#what-s-next) section of the advanced installation guide to deploy your router, registry, and other components.
## Overriding detected ip addresses and hostnames
Some deployments will require that the user override the detected hostnames
diff --git a/README_libvirt.md b/README_libvirt.md
index 60af0ac88..18ec66f2a 100644
--- a/README_libvirt.md
+++ b/README_libvirt.md
@@ -68,9 +68,14 @@ If your `$HOME` is world readable, everything is fine. If your `$HOME` is privat
error: Cannot access storage file '$HOME/libvirt-storage-pool-openshift/lenaic-master-216d8.qcow2' (as uid:99, gid:78): Permission denied
```
-In order to fix that issue, you have several possibilities:* set `libvirt_storage_pool_path` inside `playbooks/libvirt/openshift-cluster/launch.yml` and `playbooks/libvirt/openshift-cluster/terminate.yml` to a directory: * backed by a filesystem with a lot of free disk space * writable by your user; * accessible by the qemu user.* Grant the qemu user access to the storage pool.
+In order to fix that issue, you have several possibilities:
+ * set `libvirt_storage_pool_path` inside `playbooks/libvirt/openshift-cluster/launch.yml` and `playbooks/libvirt/openshift-cluster/terminate.yml` to a directory:
+ * backed by a filesystem with a lot of free disk space
+ * writable by your user;
+ * accessible by the qemu user.
+ * Grant the qemu user access to the storage pool.
-On Arch:
+On Arch or Fedora 22+:
```
setfacl -m g:kvm:--x ~
@@ -89,7 +94,8 @@ dns=dnsmasq
- Configure dnsmasq to use the Virtual Network router for example.com:
```sh
-sudo vi /etc/NetworkManager/dnsmasq.d/libvirt_dnsmasq.conf server=/example.com/192.168.55.1
+sudo vi /etc/NetworkManager/dnsmasq.d/libvirt_dnsmasq.conf
+server=/example.com/192.168.55.1
```
Test The Setup
diff --git a/README_origin.md b/README_origin.md
index f13fe660a..cb213a93a 100644
--- a/README_origin.md
+++ b/README_origin.md
@@ -73,6 +73,7 @@ osv3-master.example.com
# host group for nodes
[nodes]
+osv3-master.example.com
osv3-node[1:2].example.com
```
@@ -88,23 +89,8 @@ ansible-playbook playbooks/byo/config.yml
inventory file use the -i option for ansible-playbook.
## Post-ansible steps
-#### Create the default router
-On the master host:
-```sh
-oadm router --create=true \
- --credentials=/etc/openshift/master/openshift-router.kubeconfig
-```
-
-#### Create the default docker-registry
-On the master host:
-```sh
-oadm registry --create=true \
- --credentials=/etc/openshift/master/openshift-registry.kubeconfig
-```
-If you would like persistent storage, refer to the
-[OpenShift documentation](https://docs.openshift.org/latest/admin_guide/install/docker_registry.html)
-for more information on deployment options for the built in docker-registry.
+You should now be ready to follow the [What's Next?](https://docs.openshift.org/latest/install_config/install/advanced_install.html#what-s-next) section of the advanced installation guide to deploy your router, registry, and other components.
## Overriding detected ip addresses and hostnames
Some deployments will require that the user override the detected hostnames
diff --git a/bin/cluster b/bin/cluster
index a19434e21..59a6755d3 100755
--- a/bin/cluster
+++ b/bin/cluster
@@ -5,6 +5,7 @@ import argparse
import ConfigParser
import os
import sys
+import subprocess
import traceback
@@ -53,7 +54,6 @@ class Cluster(object):
"""
Create an OpenShift cluster for given provider
:param args: command line arguments provided by user
- :return: exit status from run command
"""
env = {'cluster_id': args.cluster_id,
'deployment_type': self.get_deployment_type(args)}
@@ -65,65 +65,60 @@ class Cluster(object):
env['num_infra'] = args.infra
env['num_etcd'] = args.etcd
- return self.action(args, inventory, env, playbook)
+ self.action(args, inventory, env, playbook)
def terminate(self, args):
"""
Destroy OpenShift cluster
:param args: command line arguments provided by user
- :return: exit status from run command
"""
env = {'cluster_id': args.cluster_id,
'deployment_type': self.get_deployment_type(args)}
playbook = "playbooks/{}/openshift-cluster/terminate.yml".format(args.provider)
inventory = self.setup_provider(args.provider)
- return self.action(args, inventory, env, playbook)
+ self.action(args, inventory, env, playbook)
def list(self, args):
"""
List VMs in cluster
:param args: command line arguments provided by user
- :return: exit status from run command
"""
env = {'cluster_id': args.cluster_id,
'deployment_type': self.get_deployment_type(args)}
playbook = "playbooks/{}/openshift-cluster/list.yml".format(args.provider)
inventory = self.setup_provider(args.provider)
- return self.action(args, inventory, env, playbook)
+ self.action(args, inventory, env, playbook)
def config(self, args):
"""
Configure or reconfigure OpenShift across clustered VMs
:param args: command line arguments provided by user
- :return: exit status from run command
"""
env = {'cluster_id': args.cluster_id,
'deployment_type': self.get_deployment_type(args)}
playbook = "playbooks/{}/openshift-cluster/config.yml".format(args.provider)
inventory = self.setup_provider(args.provider)
- return self.action(args, inventory, env, playbook)
+ self.action(args, inventory, env, playbook)
def update(self, args):
"""
Update to latest OpenShift across clustered VMs
:param args: command line arguments provided by user
- :return: exit status from run command
"""
env = {'cluster_id': args.cluster_id,
'deployment_type': self.get_deployment_type(args)}
playbook = "playbooks/{}/openshift-cluster/update.yml".format(args.provider)
inventory = self.setup_provider(args.provider)
- return self.action(args, inventory, env, playbook)
+ self.action(args, inventory, env, playbook)
def service(self, args):
"""
Make the same service call across all nodes in the cluster
:param args: command line arguments provided by user
- :return: exit status from run command
"""
env = {'cluster_id': args.cluster_id,
'deployment_type': self.get_deployment_type(args),
@@ -132,7 +127,7 @@ class Cluster(object):
playbook = "playbooks/{}/openshift-cluster/service.yml".format(args.provider)
inventory = self.setup_provider(args.provider)
- return self.action(args, inventory, env, playbook)
+ self.action(args, inventory, env, playbook)
def setup_provider(self, provider):
"""
@@ -142,10 +137,14 @@ class Cluster(object):
"""
config = ConfigParser.ConfigParser()
if 'gce' == provider:
- config.readfp(open('inventory/gce/hosts/gce.ini'))
+ gce_ini_default_path = os.path.join(
+ 'inventory/gce/hosts/gce.ini')
+ gce_ini_path = os.environ.get('GCE_INI_PATH', gce_ini_default_path)
+ if os.path.exists(gce_ini_path):
+ config.readfp(open(gce_ini_path))
- for key in config.options('gce'):
- os.environ[key] = config.get('gce', key)
+ for key in config.options('gce'):
+ os.environ[key] = config.get('gce', key)
inventory = '-i inventory/gce/hosts'
elif 'aws' == provider:
@@ -183,7 +182,6 @@ class Cluster(object):
:param inventory: derived provider library
:param env: environment variables for kubernetes
:param playbook: ansible playbook to execute
- :return: exit status from ansible-playbook command
"""
verbose = ''
@@ -213,7 +211,18 @@ class Cluster(object):
sys.stderr.write('RUN [{}]\n'.format(command))
sys.stderr.flush()
- return os.system(command)
+ try:
+ subprocess.check_call(command, shell=True)
+ except subprocess.CalledProcessError as exc:
+ raise ActionFailed("ACTION [{}] failed: {}"
+ .format(args.action, exc))
+
+
+class ActionFailed(Exception):
+ """
+ Raised when action failed.
+ """
+ pass
if __name__ == '__main__':
@@ -260,7 +269,7 @@ if __name__ == '__main__':
choices=['origin', 'online', 'enterprise'],
help='Deployment type. (default: origin)')
meta_parser.add_argument('-T', '--product-type',
- choices=['openshift' 'atomic-enterprise'],
+ choices=['openshift', 'atomic-enterprise'],
help='Product type. (default: openshift)')
meta_parser.add_argument('-o', '--option', action='append',
help='options')
@@ -328,14 +337,11 @@ if __name__ == '__main__':
sys.stderr.write('\nACTION [update] aborted by user!\n')
exit(1)
- status = 1
try:
- status = args.func(args)
- if status != 0:
- sys.stderr.write("ACTION [{}] failed with exit status {}\n".format(args.action, status))
- except Exception, e:
+ args.func(args)
+ except Exception as exc:
if args.verbose:
traceback.print_exc(file=sys.stderr)
else:
- sys.stderr.write("{}\n".format(e))
- exit(status)
+ print >>sys.stderr, exc
+ exit(1)
diff --git a/inventory/gce/hosts/gce.py b/inventory/gce/hosts/gce.py
index 3403f735e..6ed12e011 100755
--- a/inventory/gce/hosts/gce.py
+++ b/inventory/gce/hosts/gce.py
@@ -120,6 +120,7 @@ class GceInventory(object):
os.path.dirname(os.path.realpath(__file__)), "gce.ini")
gce_ini_path = os.environ.get('GCE_INI_PATH', gce_ini_default_path)
+
# Create a ConfigParser.
# This provides empty defaults to each key, so that environment
# variable configuration (as opposed to INI configuration) is able
@@ -173,6 +174,7 @@ class GceInventory(object):
args[1] = os.environ.get('GCE_PEM_FILE_PATH', args[1])
kwargs['project'] = os.environ.get('GCE_PROJECT', kwargs['project'])
+
# Retrieve and return the GCE driver.
gce = get_driver(Provider.GCE)(*args, **kwargs)
gce.connection.user_agent_append(
@@ -211,7 +213,8 @@ class GceInventory(object):
'gce_image': inst.image,
'gce_machine_type': inst.size,
'gce_private_ip': inst.private_ips[0],
- 'gce_public_ip': inst.public_ips[0],
+ # Hosts don't always have a public IP name
+ #'gce_public_ip': inst.public_ips[0],
'gce_name': inst.name,
'gce_description': inst.extra['description'],
'gce_status': inst.extra['status'],
@@ -219,8 +222,8 @@ class GceInventory(object):
'gce_tags': inst.extra['tags'],
'gce_metadata': md,
'gce_network': net,
- # Hosts don't have a public name, so we add an IP
- 'ansible_ssh_host': inst.public_ips[0]
+ # Hosts don't always have a public IP name
+ #'ansible_ssh_host': inst.public_ips[0]
}
def get_instance(self, instance_name):
diff --git a/inventory/openstack/hosts/nova.py b/inventory/openstack/hosts/nova.py
index d5bd8d1ee..3197a57bc 100755
--- a/inventory/openstack/hosts/nova.py
+++ b/inventory/openstack/hosts/nova.py
@@ -34,7 +34,7 @@ except ImportError:
# executed with no parameters, return the list of
# all groups and hosts
-NOVA_CONFIG_FILES = [os.getcwd() + "/nova.ini",
+NOVA_CONFIG_FILES = [os.path.join(os.path.dirname(os.path.realpath(__file__)), "nova.ini"),
os.path.expanduser(os.environ.get('ANSIBLE_CONFIG', "~/nova.ini")),
"/etc/ansible/nova.ini"]
diff --git a/playbooks/adhoc/docker_loopback_to_lvm/docker-storage-setup b/playbooks/adhoc/docker_loopback_to_lvm/docker-storage-setup
new file mode 100644
index 000000000..059058823
--- /dev/null
+++ b/playbooks/adhoc/docker_loopback_to_lvm/docker-storage-setup
@@ -0,0 +1,2 @@
+DEVS=/dev/xvdb
+VG=docker_vg
diff --git a/playbooks/adhoc/docker_loopback_to_lvm/docker_loopback_to_direct_lvm.yml b/playbooks/adhoc/docker_loopback_to_lvm/docker_loopback_to_direct_lvm.yml
new file mode 100644
index 000000000..b6a2d2f26
--- /dev/null
+++ b/playbooks/adhoc/docker_loopback_to_lvm/docker_loopback_to_direct_lvm.yml
@@ -0,0 +1,142 @@
+---
+# This playbook coverts docker to go from loopback to direct-lvm (the Red Hat recommended way to run docker)
+# in AWS. This adds an additional EBS volume and creates the Volume Group on this EBS volume to use.
+#
+# To run:
+# 1. Source your AWS credentials (make sure it's the corresponding AWS account) into your environment
+# export AWS_ACCESS_KEY_ID='XXXXX'
+# export AWS_SECRET_ACCESS_KEY='XXXXXX'
+#
+# 2. run the playbook:
+# ansible-playbook -e 'cli_tag_name=<tag-name>' -e "cli_volume_size=30" docker_loopback_to_direct_lvm.yml
+#
+# Example:
+# ansible-playbook -e 'cli_tag_name=ops-master-12345' -e "cli_volume_size=30" docker_loopback_to_direct_lvm.yml
+#
+# Notes:
+# * By default this will do a 30GB volume.
+# * iops are calculated by Disk Size * 30. e.g ( 30GB * 30) = 900 iops
+# * This will remove /var/lib/docker!
+# * You may need to re-deploy docker images after this is run (like monitoring)
+#
+
+- name: Fix docker to have a provisioned iops drive
+ hosts: "tag_Name_{{ cli_tag_name }}"
+ user: root
+ connection: ssh
+ gather_facts: no
+
+ vars:
+ cli_volume_type: gp2
+ cli_volume_size: 30
+
+ pre_tasks:
+ - fail:
+ msg: "This playbook requires {{item}} to be set."
+ when: "{{ item }} is not defined or {{ item }} == ''"
+ with_items:
+ - cli_tag_name
+ - cli_volume_size
+
+ - debug:
+ var: hosts
+
+ - name: start docker
+ service:
+ name: docker
+ state: started
+
+ - name: Determine if loopback
+ shell: docker info | grep 'Data file:.*loop'
+ register: loop_device_check
+ ignore_errors: yes
+
+ - debug:
+ var: loop_device_check
+
+ - name: fail if we don't detect loopback
+ fail:
+ msg: loopback not detected! Please investigate manually.
+ when: loop_device_check.rc == 1
+
+ - name: stop zagg client monitoring container
+ service:
+ name: oso-rhel7-zagg-client
+ state: stopped
+ ignore_errors: yes
+
+ - name: stop pcp client monitoring container
+ service:
+ name: oso-f22-host-monitoring
+ state: stopped
+ ignore_errors: yes
+
+ - name: stop docker
+ service:
+ name: docker
+ state: stopped
+
+ - name: delete /var/lib/docker
+ command: rm -rf /var/lib/docker
+
+ - name: remove /var/lib/docker
+ command: rm -rf /var/lib/docker
+
+ - name: check to see if /dev/xvdb exists
+ command: test -e /dev/xvdb
+ register: xvdb_check
+ ignore_errors: yes
+
+ - debug: var=xvdb_check
+
+ - name: fail if /dev/xvdb already exists
+ fail:
+ msg: /dev/xvdb already exists. Please investigate
+ when: xvdb_check.rc == 0
+
+ - name: Create a volume and attach it
+ delegate_to: localhost
+ ec2_vol:
+ state: present
+ instance: "{{ ec2_id }}"
+ region: "{{ ec2_region }}"
+ volume_size: "{{ cli_volume_size | default(30, True)}}"
+ volume_type: "{{ cli_volume_type }}"
+ device_name: /dev/xvdb
+ register: vol
+
+ - debug: var=vol
+
+ - name: tag the vol with a name
+ delegate_to: localhost
+ ec2_tag: region={{ ec2_region }} resource={{ vol.volume_id }}
+ args:
+ tags:
+ Name: "{{ ec2_tag_Name }}"
+ env: "{{ ec2_tag_environment }}"
+ register: voltags
+
+ - name: Wait for volume to attach
+ pause:
+ seconds: 30
+
+ - name: copy the docker-storage-setup config file
+ copy:
+ src: docker-storage-setup
+ dest: /etc/sysconfig/docker-storage-setup
+ owner: root
+ group: root
+ mode: 0664
+
+ - name: docker storage setup
+ command: docker-storage-setup
+ register: setup_output
+
+ - debug: var=setup_output
+
+ - name: start docker
+ command: systemctl start docker.service
+ register: dockerstart
+
+ - debug: var=dockerstart
+
diff --git a/playbooks/adhoc/docker_loopback_to_lvm/ops-docker-loopback-to-direct-lvm.yml b/playbooks/adhoc/docker_loopback_to_lvm/ops-docker-loopback-to-direct-lvm.yml
new file mode 100755
index 000000000..614b2537a
--- /dev/null
+++ b/playbooks/adhoc/docker_loopback_to_lvm/ops-docker-loopback-to-direct-lvm.yml
@@ -0,0 +1,104 @@
+#!/usr/bin/ansible-playbook
+---
+# This playbook coverts docker to go from loopback to direct-lvm (the Red Hat recommended way to run docker).
+#
+# It requires the block device to be already provisioned and attached to the host. This is a generic playbook,
+# meant to be used for manual conversion. For AWS specific conversions, use the other playbook in this directory.
+#
+# To run:
+# ./ops-docker-loopback-to-direct-lvm.yml -e cli_host=<host to run on> -e cli_docker_device=<path to device>
+#
+# Example:
+# ./ops-docker-loopback-to-direct-lvm.yml -e cli_host=twiesttest-master-fd32 -e cli_docker_device=/dev/sdb
+#
+# Notes:
+# * This will remove /var/lib/docker!
+# * You may need to re-deploy docker images after this is run (like monitoring)
+
+- name: Fix docker to have a provisioned iops drive
+ hosts: "{{ cli_name }}"
+ user: root
+ connection: ssh
+ gather_facts: no
+
+ pre_tasks:
+ - fail:
+ msg: "This playbook requires {{item}} to be set."
+ when: "{{ item }} is not defined or {{ item }} == ''"
+ with_items:
+ - cli_docker_device
+
+ - name: start docker
+ service:
+ name: docker
+ state: started
+
+ - name: Determine if loopback
+ shell: docker info | grep 'Data file:.*loop'
+ register: loop_device_check
+ ignore_errors: yes
+
+ - debug:
+ var: loop_device_check
+
+ - name: fail if we don't detect loopback
+ fail:
+ msg: loopback not detected! Please investigate manually.
+ when: loop_device_check.rc == 1
+
+ - name: stop zagg client monitoring container
+ service:
+ name: oso-rhel7-zagg-client
+ state: stopped
+ ignore_errors: yes
+
+ - name: stop pcp client monitoring container
+ service:
+ name: oso-f22-host-monitoring
+ state: stopped
+ ignore_errors: yes
+
+ - name: "check to see if {{ cli_docker_device }} exists"
+ command: "test -e {{ cli_docker_device }}"
+ register: docker_dev_check
+ ignore_errors: yes
+
+ - debug: var=docker_dev_check
+
+ - name: "fail if {{ cli_docker_device }} doesn't exist"
+ fail:
+ msg: "{{ cli_docker_device }} doesn't exist. Please investigate"
+ when: docker_dev_check.rc != 0
+
+ - name: stop docker
+ service:
+ name: docker
+ state: stopped
+
+ - name: delete /var/lib/docker
+ command: rm -rf /var/lib/docker
+
+ - name: remove /var/lib/docker
+ command: rm -rf /var/lib/docker
+
+ - name: copy the docker-storage-setup config file
+ copy:
+ content: >
+ DEVS={{ cli_docker_device }}
+ VG=docker_vg
+ dest: /etc/sysconfig/docker-storage-setup
+ owner: root
+ group: root
+ mode: 0664
+
+ - name: docker storage setup
+ command: docker-storage-setup
+ register: setup_output
+
+ - debug: var=setup_output
+
+ - name: start docker
+ command: systemctl start docker.service
+ register: dockerstart
+
+ - debug: var=dockerstart
diff --git a/playbooks/adhoc/docker_storage_cleanup/docker_storage_cleanup.yml b/playbooks/adhoc/docker_storage_cleanup/docker_storage_cleanup.yml
new file mode 100644
index 000000000..a19291a9f
--- /dev/null
+++ b/playbooks/adhoc/docker_storage_cleanup/docker_storage_cleanup.yml
@@ -0,0 +1,69 @@
+---
+# This playbook attempts to cleanup unwanted docker files to help alleviate docker disk space issues.
+#
+# To run:
+#
+# 1. run the playbook:
+#
+# ansible-playbook -e 'cli_tag_name=<tag-name>' docker_storage_cleanup.yml
+#
+# Example:
+#
+# ansible-playbook -e 'cli_tag_name=ops-node-compute-12345' docker_storage_cleanup.yml
+#
+# Notes:
+# * This *should* not interfere with running docker images
+#
+
+- name: Clean up Docker Storage
+ gather_facts: no
+ hosts: "tag_Name_{{ cli_tag_name }}"
+ user: root
+ connection: ssh
+
+ pre_tasks:
+
+ - fail:
+ msg: "This playbook requires {{item}} to be set."
+ when: "{{ item }} is not defined or {{ item }} == ''"
+ with_items:
+ - cli_tag_name
+
+ - name: Ensure docker is running
+ service:
+ name: docker
+ state: started
+ enabled: yes
+
+ - name: Get docker info
+ command: docker info
+ register: docker_info
+
+ - name: Show docker info
+ debug:
+ var: docker_info.stdout_lines
+
+ - name: Remove exited and dead containers
+ shell: "docker ps -a | awk '/Exited|Dead/ {print $1}' | xargs --no-run-if-empty docker rm"
+ ignore_errors: yes
+
+ - name: Remove dangling docker images
+ shell: "docker images -q -f dangling=true | xargs --no-run-if-empty docker rmi"
+ ignore_errors: yes
+
+ - name: Remove non-running docker images
+ shell: "docker images | grep -v -e registry.access.redhat.com -e docker-registry.usersys.redhat.com -e docker-registry.ops.rhcloud.com | awk '{print $3}' | xargs --no-run-if-empty docker rmi 2>/dev/null"
+ ignore_errors: yes
+
+ # leaving off the '-t' for docker exec. With it, it doesn't work with ansible and tty support
+ - name: update zabbix docker items
+ command: docker exec -i oso-rhel7-zagg-client /usr/local/bin/cron-send-docker-metrics.py
+
+ # Get and show docker info again.
+ - name: Get docker info
+ command: docker info
+ register: docker_info
+
+ - name: Show docker info
+ debug:
+ var: docker_info.stdout_lines
diff --git a/playbooks/adhoc/grow_docker_vg/filter_plugins/oo_filters.py b/playbooks/adhoc/grow_docker_vg/filter_plugins/oo_filters.py
new file mode 100644
index 000000000..d0264cde9
--- /dev/null
+++ b/playbooks/adhoc/grow_docker_vg/filter_plugins/oo_filters.py
@@ -0,0 +1,41 @@
+#!/usr/bin/python
+# -*- coding: utf-8 -*-
+# vim: expandtab:tabstop=4:shiftwidth=4
+'''
+Custom filters for use in openshift-ansible
+'''
+
+import pdb
+
+
+class FilterModule(object):
+ ''' Custom ansible filters '''
+
+ @staticmethod
+ def oo_pdb(arg):
+ ''' This pops you into a pdb instance where arg is the data passed in
+ from the filter.
+ Ex: "{{ hostvars | oo_pdb }}"
+ '''
+ pdb.set_trace()
+ return arg
+
+ @staticmethod
+ def translate_volume_name(volumes, target_volume):
+ '''
+ This filter matches a device string /dev/sdX to /dev/xvdX
+ It will then return the AWS volume ID
+ '''
+ for vol in volumes:
+ translated_name = vol["attachment_set"]["device"].replace("/dev/sd", "/dev/xvd")
+ if target_volume.startswith(translated_name):
+ return vol["id"]
+
+ return None
+
+
+ def filters(self):
+ ''' returns a mapping of filters to methods '''
+ return {
+ "translate_volume_name": self.translate_volume_name,
+ }
diff --git a/playbooks/adhoc/grow_docker_vg/grow_docker_vg.yml b/playbooks/adhoc/grow_docker_vg/grow_docker_vg.yml
new file mode 100644
index 000000000..63d473146
--- /dev/null
+++ b/playbooks/adhoc/grow_docker_vg/grow_docker_vg.yml
@@ -0,0 +1,206 @@
+---
+# This playbook grows the docker VG on a node by:
+# * add a new volume
+# * add volume to the existing VG.
+# * pv move to the new volume.
+# * remove old volume
+# * detach volume
+# * mark old volume in AWS with "REMOVE ME" tag
+# * grow docker LVM to 90% of the VG
+#
+# To run:
+# 1. Source your AWS credentials (make sure it's the corresponding AWS account) into your environment
+# export AWS_ACCESS_KEY_ID='XXXXX'
+# export AWS_SECRET_ACCESS_KEY='XXXXXX'
+#
+# 2. run the playbook:
+# ansible-playbook -e 'cli_tag_name=<tag-name>' grow_docker_vg.yml
+#
+# Example:
+# ansible-playbook -e 'cli_tag_name=ops-compute-12345' grow_docker_vg.yml
+#
+# Notes:
+# * By default this will do a 55GB GP2 volume. The can be overidden with the "-e 'cli_volume_size=100'" variable
+# * This does a GP2 by default. Support for Provisioned IOPS has not been added
+# * This will assign the new volume to /dev/xvdc. This is not variablized, yet.
+# * This can be done with NO downtime on the host
+# * This playbook assumes that there is a Logical Volume that is installed and called "docker-pool". This is
+# the LV that gets created via the "docker-storage-setup" command
+#
+
+- name: Grow the docker volume group
+ hosts: "tag_Name_{{ cli_tag_name }}"
+ user: root
+ connection: ssh
+ gather_facts: no
+
+ vars:
+ cli_volume_type: gp2
+ cli_volume_size: 55
+# cli_volume_iops: "{{ 30 * cli_volume_size }}"
+
+ pre_tasks:
+ - fail:
+ msg: "This playbook requires {{item}} to be set."
+ when: "{{ item }} is not defined or {{ item }} == ''"
+ with_items:
+ - cli_tag_name
+ - cli_volume_size
+
+ - debug:
+ var: hosts
+
+ - name: start docker
+ service:
+ name: docker
+ state: started
+
+ - name: Determine if Storage Driver (docker info) is devicemapper
+ shell: docker info | grep 'Storage Driver:.*devicemapper'
+ register: device_mapper_check
+ ignore_errors: yes
+
+ - debug:
+ var: device_mapper_check
+
+ - name: fail if we don't detect devicemapper
+ fail:
+ msg: The "Storage Driver" in "docker info" is not set to "devicemapper"! Please investigate manually.
+ when: device_mapper_check.rc == 1
+
+ # docker-storage-setup creates a docker-pool as the lvm. I am using docker-pool lvm to test
+ # and find the volume group.
+ - name: Attempt to find the Volume Group that docker is using
+ shell: lvs | grep docker-pool | awk '{print $2}'
+ register: docker_vg_name
+ ignore_errors: yes
+
+ - debug:
+ var: docker_vg_name
+
+ - name: fail if we don't find a docker volume group
+ fail:
+ msg: Unable to find docker volume group. Please investigate manually.
+ when: docker_vg_name.stdout_lines|length != 1
+
+ # docker-storage-setup creates a docker-pool as the lvm. I am using docker-pool lvm to test
+ # and find the physical volume.
+ - name: Attempt to find the Phyisical Volume that docker is using
+ shell: "pvs | grep {{ docker_vg_name.stdout }} | awk '{print $1}'"
+ register: docker_pv_name
+ ignore_errors: yes
+
+ - debug:
+ var: docker_pv_name
+
+ - name: fail if we don't find a docker physical volume
+ fail:
+ msg: Unable to find docker physical volume. Please investigate manually.
+ when: docker_pv_name.stdout_lines|length != 1
+
+
+ - name: get list of volumes from AWS
+ delegate_to: localhost
+ ec2_vol:
+ state: list
+ instance: "{{ ec2_id }}"
+ region: "{{ ec2_region }}"
+ register: attached_volumes
+
+ - debug: var=attached_volumes
+
+ - name: get volume id of current docker volume
+ set_fact:
+ old_docker_volume_id: "{{ attached_volumes.volumes | translate_volume_name(docker_pv_name.stdout) }}"
+
+ - debug: var=old_docker_volume_id
+
+ - name: check to see if /dev/xvdc exists
+ command: test -e /dev/xvdc
+ register: xvdc_check
+ ignore_errors: yes
+
+ - debug: var=xvdc_check
+
+ - name: fail if /dev/xvdc already exists
+ fail:
+ msg: /dev/xvdc already exists. Please investigate
+ when: xvdc_check.rc == 0
+
+ - name: Create a volume and attach it
+ delegate_to: localhost
+ ec2_vol:
+ state: present
+ instance: "{{ ec2_id }}"
+ region: "{{ ec2_region }}"
+ volume_size: "{{ cli_volume_size | default(30, True)}}"
+ volume_type: "{{ cli_volume_type }}"
+ device_name: /dev/xvdc
+ register: create_volume
+
+ - debug: var=create_volume
+
+ - name: Fail when problems creating volumes and attaching
+ fail:
+ msg: "Failed to create or attach volume msg: {{ create_volume.msg }}"
+ when: create_volume.msg is defined
+
+ - name: tag the vol with a name
+ delegate_to: localhost
+ ec2_tag: region={{ ec2_region }} resource={{ create_volume.volume_id }}
+ args:
+ tags:
+ Name: "{{ ec2_tag_Name }}"
+ env: "{{ ec2_tag_environment }}"
+ register: voltags
+
+ - name: check for attached drive
+ command: test -b /dev/xvdc
+ register: attachment_check
+ until: attachment_check.rc == 0
+ retries: 30
+ delay: 2
+
+ - name: partition the new drive and make it lvm
+ command: parted /dev/xvdc --script -- mklabel msdos mkpart primary 0% 100% set 1 lvm
+
+ - name: pvcreate /dev/xvdc
+ command: pvcreate /dev/xvdc1
+
+ - name: Extend the docker volume group
+ command: vgextend "{{ docker_vg_name.stdout }}" /dev/xvdc1
+
+ - name: pvmove onto new volume
+ command: "pvmove {{ docker_pv_name.stdout }} /dev/xvdc1"
+ async: 43200
+ poll: 10
+
+ - name: Remove the old docker drive from the volume group
+ command: "vgreduce {{ docker_vg_name.stdout }} {{ docker_pv_name.stdout }}"
+
+ - name: Remove the pv from the old drive
+ command: "pvremove {{ docker_pv_name.stdout }}"
+
+ - name: Extend the docker lvm
+ command: "lvextend -l '90%VG' /dev/{{ docker_vg_name.stdout }}/docker-pool"
+
+ - name: detach old docker volume
+ delegate_to: localhost
+ ec2_vol:
+ region: "{{ ec2_region }}"
+ id: "{{ old_docker_volume_id }}"
+ instance: None
+
+ - name: tag the old vol valid label
+ delegate_to: localhost
+ ec2_tag: region={{ ec2_region }} resource={{old_docker_volume_id}}
+ args:
+ tags:
+ Name: "{{ ec2_tag_Name }} REMOVE ME"
+ register: voltags
+
+ - name: Update the /etc/sysconfig/docker-storage-setup with new device
+ lineinfile:
+ dest: /etc/sysconfig/docker-storage-setup
+ regexp: ^DEVS=
+ line: DEVS=/dev/xvdc
diff --git a/playbooks/adhoc/s3_registry/s3_registry.j2 b/playbooks/adhoc/s3_registry/s3_registry.j2
new file mode 100644
index 000000000..acfa89515
--- /dev/null
+++ b/playbooks/adhoc/s3_registry/s3_registry.j2
@@ -0,0 +1,20 @@
+version: 0.1
+log:
+ level: debug
+http:
+ addr: :5000
+storage:
+ cache:
+ layerinfo: inmemory
+ s3:
+ accesskey: {{ aws_access_key }}
+ secretkey: {{ aws_secret_key }}
+ region: us-east-1
+ bucket: {{ clusterid }}-docker
+ encrypt: true
+ secure: true
+ v4auth: true
+ rootdirectory: /registry
+middleware:
+ repository:
+ - name: openshift
diff --git a/playbooks/adhoc/s3_registry/s3_registry.yml b/playbooks/adhoc/s3_registry/s3_registry.yml
new file mode 100644
index 000000000..5dc1abf17
--- /dev/null
+++ b/playbooks/adhoc/s3_registry/s3_registry.yml
@@ -0,0 +1,61 @@
+---
+# This playbook creates an S3 bucket named after your cluster and configures the docker-registry service to use the bucket as its backend storage.
+# Usage:
+# ansible-playbook s3_registry.yml -e clusterid="mycluster"
+#
+# The AWS access/secret keys should be the keys of a separate user (not your main user), containing only the necessary S3 access role.
+# The 'clusterid' is the short name of your cluster.
+
+- hosts: security_group_{{ clusterid }}_master
+ remote_user: root
+ gather_facts: False
+
+ vars:
+ aws_access_key: "{{ lookup('env', 'AWS_ACCESS_KEY_ID') }}"
+ aws_secret_key: "{{ lookup('env', 'AWS_SECRET_ACCESS_KEY') }}"
+ tasks:
+
+ - name: Check for AWS creds
+ fail:
+ msg: "Couldn't find {{ item }} creds in ENV"
+ when: "{{ item }} == ''"
+ with_items:
+ - aws_access_key
+ - aws_secret_key
+
+ - name: Create S3 bucket
+ local_action:
+ module: s3 bucket="{{ clusterid }}-docker" mode=create
+
+ - name: Generate docker registry config
+ template: src="s3_registry.j2" dest="/root/config.yml" owner=root mode=0600
+
+ - name: Determine if new secrets are needed
+ command: oc get secrets
+ register: secrets
+
+ - name: Create registry secrets
+ command: oc secrets new dockerregistry /root/config.yml
+ when: "'dockerregistry' not in secrets.stdout"
+
+ - name: Determine if service account contains secrets
+ command: oc describe serviceaccount/registry
+ register: serviceaccount
+
+ - name: Add secrets to registry service account
+ command: oc secrets add serviceaccount/registry secrets/dockerregistry
+ when: "'dockerregistry' not in serviceaccount.stdout"
+
+ - name: Determine if deployment config contains secrets
+ command: oc volume dc/docker-registry --list
+ register: dc
+
+ - name: Add secrets to registry deployment config
+ command: oc volume dc/docker-registry --add --name=dockersecrets -m /etc/registryconfig --type=secret --secret-name=dockerregistry
+ when: "'dockersecrets' not in dc.stdout"
+
+ - name: Scale up registry
+ command: oc scale --replicas=1 dc/docker-registry
+
+ - name: Delete temporary config file
+ file: path=/root/config.yml state=absent
diff --git a/playbooks/adhoc/upgrades/README.md b/playbooks/adhoc/upgrades/README.md
new file mode 100644
index 000000000..6de8a970f
--- /dev/null
+++ b/playbooks/adhoc/upgrades/README.md
@@ -0,0 +1,21 @@
+# [NOTE]
+This playbook will re-run installation steps overwriting any local
+modifications. You should ensure that your inventory has been updated with any
+modifications you've made after your initial installation. If you find any items
+that cannot be configured via ansible please open an issue at
+https://github.com/openshift/openshift-ansible
+
+# Overview
+This playbook is available as a technical preview. It currently performs the
+following steps.
+
+ * Upgrade and restart master services
+ * Upgrade and restart node services
+ * Applies latest configuration by re-running the installation playbook
+ * Applies the latest cluster policies
+ * Updates the default router if one exists
+ * Updates the default registry if one exists
+ * Updates image streams and quickstarts
+
+# Usage
+ansible-playbook -i ~/ansible-inventory openshift-ansible/playbooks/adhoc/upgrades/upgrade.yml
diff --git a/playbooks/adhoc/upgrades/filter_plugins b/playbooks/adhoc/upgrades/filter_plugins
new file mode 120000
index 000000000..b0b7a3414
--- /dev/null
+++ b/playbooks/adhoc/upgrades/filter_plugins
@@ -0,0 +1 @@
+../../../filter_plugins/ \ No newline at end of file
diff --git a/playbooks/adhoc/upgrades/lookup_plugins b/playbooks/adhoc/upgrades/lookup_plugins
new file mode 120000
index 000000000..73cafffe5
--- /dev/null
+++ b/playbooks/adhoc/upgrades/lookup_plugins
@@ -0,0 +1 @@
+../../../lookup_plugins/ \ No newline at end of file
diff --git a/playbooks/adhoc/upgrades/roles b/playbooks/adhoc/upgrades/roles
new file mode 120000
index 000000000..e2b799b9d
--- /dev/null
+++ b/playbooks/adhoc/upgrades/roles
@@ -0,0 +1 @@
+../../../roles/ \ No newline at end of file
diff --git a/playbooks/adhoc/upgrades/upgrade.yml b/playbooks/adhoc/upgrades/upgrade.yml
new file mode 100644
index 000000000..e666f0472
--- /dev/null
+++ b/playbooks/adhoc/upgrades/upgrade.yml
@@ -0,0 +1,115 @@
+---
+- name: Re-Run cluster configuration to apply latest configuration changes
+ include: ../../common/openshift-cluster/config.yml
+ vars:
+ g_etcd_group: "{{ 'etcd' }}"
+ g_masters_group: "{{ 'masters' }}"
+ g_nodes_group: "{{ 'nodes' }}"
+ openshift_cluster_id: "{{ cluster_id | default('default') }}"
+ openshift_deployment_type: "{{ deployment_type }}"
+
+- name: Upgrade masters
+ hosts: masters
+ vars:
+ openshift_version: "{{ openshift_pkg_version | default('') }}"
+ tasks:
+ - name: Upgrade master packages
+ yum: pkg={{ openshift.common.service_type }}-master{{ openshift_version }} state=latest
+ - name: Restart master services
+ service: name="{{ openshift.common.service_type}}-master" state=restarted
+
+- name: Upgrade nodes
+ hosts: nodes
+ vars:
+ openshift_version: "{{ openshift_pkg_version | default('') }}"
+ tasks:
+ - name: Upgrade node packages
+ yum: pkg={{ openshift.common.service_type }}-node{{ openshift_version }} state=latest
+ - name: Restart node services
+ service: name="{{ openshift.common.service_type }}-node" state=restarted
+
+- name: Determine new master version
+ hosts: oo_first_master
+ tasks:
+ - name: Determine new version
+ command: >
+ rpm -q --queryformat '%{version}' {{ openshift.common.service_type }}-master
+ register: _new_version
+
+- name: Ensure AOS 3.0.2 or Origin 1.0.6
+ hosts: oo_first_master
+ tasks:
+ fail: This playbook requires Origin 1.0.6 or Atomic OpenShift 3.0.2 or later
+ when: _new_version.stdout < 1.0.6 or (_new_version.stdout >= 3.0 and _new_version.stdout < 3.0.2)
+
+- name: Update cluster policy
+ hosts: oo_first_master
+ tasks:
+ - name: oadm policy reconcile-cluster-roles --confirm
+ command: >
+ {{ openshift.common.admin_binary}} --config={{ openshift.common.config_base }}/master/admin.kubeconfig
+ policy reconcile-cluster-roles --confirm
+
+- name: Upgrade default router
+ hosts: oo_first_master
+ vars:
+ - router_image: "{{ openshift.master.registry_url | replace( '${component}', 'haproxy-router' ) | replace ( '${version}', 'v' + _new_version.stdout ) }}"
+ - oc_cmd: "{{ openshift.common.client_binary }} --config={{ openshift.common.config_base }}/master/admin.kubeconfig"
+ tasks:
+ - name: Check for default router
+ command: >
+ {{ oc_cmd }} get -n default dc/router
+ register: _default_router
+ failed_when: false
+ changed_when: false
+ - name: Check for allowHostNetwork and allowHostPorts
+ when: _default_router.rc == 0
+ shell: >
+ {{ oc_cmd }} get -o yaml scc/privileged | /usr/bin/grep -e allowHostPorts -e allowHostNetwork
+ register: _scc
+ - name: Grant allowHostNetwork and allowHostPorts
+ when:
+ - _default_router.rc == 0
+ - "'false' in _scc.stdout"
+ command: >
+ {{ oc_cmd }} patch scc/privileged -p '{"allowHostPorts":true,"allowHostNetwork":true}' --loglevel=9
+ - name: Update deployment config to 1.0.4/3.0.1 spec
+ when: _default_router.rc == 0
+ command: >
+ {{ oc_cmd }} patch dc/router -p
+ '{"spec":{"strategy":{"rollingParams":{"updatePercent":-10},"spec":{"serviceAccount":"router","serviceAccountName":"router"}}}}'
+ - name: Switch to hostNetwork=true
+ when: _default_router.rc == 0
+ command: >
+ {{ oc_cmd }} patch dc/router -p '{"spec":{"template":{"spec":{"hostNetwork":true}}}}'
+ - name: Update router image to current version
+ when: _default_router.rc == 0
+ command: >
+ {{ oc_cmd }} patch dc/router -p
+ '{"spec":{"template":{"spec":{"containers":[{"name":"router","image":"{{ router_image }}"}]}}}}'
+
+- name: Upgrade default
+ hosts: oo_first_master
+ vars:
+ - registry_image: "{{ openshift.master.registry_url | replace( '${component}', 'docker-registry' ) | replace ( '${version}', 'v' + _new_version.stdout ) }}"
+ - oc_cmd: "{{ openshift.common.client_binary }} --config={{ openshift.common.config_base }}/master/admin.kubeconfig"
+ tasks:
+ - name: Check for default registry
+ command: >
+ {{ oc_cmd }} get -n default dc/docker-registry
+ register: _default_registry
+ failed_when: false
+ changed_when: false
+ - name: Update registry image to current version
+ when: _default_registry.rc == 0
+ command: >
+ {{ oc_cmd }} patch dc/docker-registry -p
+ '{"spec":{"template":{"spec":{"containers":[{"name":"registry","image":"{{ registry_image }}"}]}}}}'
+
+- name: Update image streams and templates
+ hosts: oo_first_master
+ vars:
+ openshift_examples_import_command: "update"
+ openshift_deployment_type: "{{ deployment_type }}"
+ roles:
+ - openshift_examples
diff --git a/playbooks/aws/openshift-cluster/tasks/launch_instances.yml b/playbooks/aws/openshift-cluster/tasks/launch_instances.yml
index b77bcdc1a..9c699120b 100644
--- a/playbooks/aws/openshift-cluster/tasks/launch_instances.yml
+++ b/playbooks/aws/openshift-cluster/tasks/launch_instances.yml
@@ -172,6 +172,7 @@
- rotate 7
- compress
- sharedscripts
+ - missingok
scripts:
postrotate: "/bin/kill -HUP `cat /var/run/syslogd.pid 2> /dev/null` 2> /dev/null || true"
diff --git a/playbooks/gce/openshift-cluster/config.yml b/playbooks/gce/openshift-cluster/config.yml
index fd5dfcc72..6ca4f7395 100644
--- a/playbooks/gce/openshift-cluster/config.yml
+++ b/playbooks/gce/openshift-cluster/config.yml
@@ -10,6 +10,8 @@
- set_fact:
g_ssh_user_tmp: "{{ deployment_vars[deployment_type].ssh_user }}"
g_sudo_tmp: "{{ deployment_vars[deployment_type].sudo }}"
+ use_sdn: "{{ do_we_use_openshift_sdn }}"
+ sdn_plugin: "{{ sdn_network_plugin }}"
- include: ../../common/openshift-cluster/config.yml
vars:
@@ -18,7 +20,10 @@
g_nodes_group: "{{ 'tag_env-host-type-' ~ cluster_id ~ '-openshift-node' }}"
g_ssh_user: "{{ hostvars.localhost.g_ssh_user_tmp }}"
g_sudo: "{{ hostvars.localhost.g_sudo_tmp }}"
+ g_nodeonmaster: true
openshift_cluster_id: "{{ cluster_id }}"
openshift_debug_level: 2
openshift_deployment_type: "{{ deployment_type }}"
openshift_hostname: "{{ gce_private_ip }}"
+ openshift_use_openshift_sdn: "{{ hostvars.localhost.use_sdn }}"
+ os_sdn_network_plugin_name: "{{ hostvars.localhost.sdn_plugin }}"
diff --git a/playbooks/gce/openshift-cluster/join_node.yml b/playbooks/gce/openshift-cluster/join_node.yml
new file mode 100644
index 000000000..0dfa3e9d7
--- /dev/null
+++ b/playbooks/gce/openshift-cluster/join_node.yml
@@ -0,0 +1,49 @@
+---
+- name: Populate oo_hosts_to_update group
+ hosts: localhost
+ gather_facts: no
+ vars_files:
+ - vars.yml
+ tasks:
+ - name: Evaluate oo_hosts_to_update
+ add_host:
+ name: "{{ node_ip }}"
+ groups: oo_hosts_to_update
+ ansible_ssh_user: "{{ deployment_vars[deployment_type].ssh_user }}"
+ ansible_sudo: "{{ deployment_vars[deployment_type].sudo }}"
+
+- include: ../../common/openshift-cluster/update_repos_and_packages.yml
+
+- name: Populate oo_masters_to_config host group
+ hosts: localhost
+ gather_facts: no
+ vars_files:
+ - vars.yml
+ tasks:
+ - name: Evaluate oo_nodes_to_config
+ add_host:
+ name: "{{ node_ip }}"
+ ansible_ssh_user: "{{ deployment_vars[deployment_type].ssh_user }}"
+ ansible_sudo: "{{ deployment_vars[deployment_type].sudo }}"
+ groups: oo_nodes_to_config
+
+ - name: Evaluate oo_first_master
+ add_host:
+ name: "{{ groups['tag_env-host-type-' ~ cluster_id ~ '-openshift-master'][0] }}"
+ ansible_ssh_user: "{{ deployment_vars[deployment_type].ssh_user }}"
+ ansible_sudo: "{{ deployment_vars[deployment_type].sudo }}"
+ groups: oo_first_master
+ when: "'tag_env-host-type-{{ cluster_id }}-openshift-master' in groups"
+
+#- include: config.yml
+- include: ../../common/openshift-node/config.yml
+ vars:
+ openshift_cluster_id: "{{ cluster_id }}"
+ openshift_debug_level: 4
+ openshift_deployment_type: "{{ deployment_type }}"
+ openshift_hostname: "{{ ansible_default_ipv4.address }}"
+ openshift_use_openshift_sdn: true
+ openshift_node_labels: "{{ lookup('oo_option', 'openshift_node_labels') }} "
+ os_sdn_network_plugin_name: "redhat/openshift-ovs-subnet"
+ osn_cluster_dns_domain: "{{ hostvars[groups.oo_first_master.0].openshift.dns.domain }}"
+ osn_cluster_dns_ip: "{{ hostvars[groups.oo_first_master.0].openshift.dns.ip }}"
diff --git a/playbooks/gce/openshift-cluster/launch.yml b/playbooks/gce/openshift-cluster/launch.yml
index 7a3b80da0..c22b897d5 100644
--- a/playbooks/gce/openshift-cluster/launch.yml
+++ b/playbooks/gce/openshift-cluster/launch.yml
@@ -34,27 +34,28 @@
count: "{{ num_infra }}"
- include: tasks/launch_instances.yml
vars:
- instances: "{{ infra_names }}"
+ instances: "{{ node_names }}"
cluster: "{{ cluster_id }}"
type: "{{ k8s_type }}"
g_sub_host_type: "{{ sub_host_type }}"
- - set_fact:
- a_infra: "{{ infra_names[0] }}"
- - add_host: name={{ a_infra }} groups=service_master
+ - add_host:
+ name: "{{ master_names.0 }}"
+ groups: service_master
+ when: master_names is defined and master_names.0 is defined
- include: update.yml
-
-- name: Deploy OpenShift Services
- hosts: service_master
- connection: ssh
- gather_facts: yes
- roles:
- - openshift_registry
- - openshift_router
-
-- include: ../../common/openshift-cluster/create_services.yml
- vars:
- g_svc_master: "{{ service_master }}"
+#
+#- name: Deploy OpenShift Services
+# hosts: service_master
+# connection: ssh
+# gather_facts: yes
+# roles:
+# - openshift_registry
+# - openshift_router
+#
+#- include: ../../common/openshift-cluster/create_services.yml
+# vars:
+# g_svc_master: "{{ service_master }}"
- include: list.yml
diff --git a/playbooks/gce/openshift-cluster/list.yml b/playbooks/gce/openshift-cluster/list.yml
index 5ba0f5a48..53b2b9a5e 100644
--- a/playbooks/gce/openshift-cluster/list.yml
+++ b/playbooks/gce/openshift-cluster/list.yml
@@ -14,11 +14,11 @@
groups: oo_list_hosts
ansible_ssh_user: "{{ deployment_vars[deployment_type].ssh_user | default(ansible_ssh_user, true) }}"
ansible_sudo: "{{ deployment_vars[deployment_type].sudo }}"
- with_items: groups[scratch_group] | default([]) | difference(['localhost']) | difference(groups.status_terminated)
+ with_items: groups[scratch_group] | default([], true) | difference(['localhost']) | difference(groups.status_terminated | default([], true))
- name: List instance(s)
hosts: oo_list_hosts
gather_facts: no
tasks:
- debug:
- msg: "public ip:{{ hostvars[inventory_hostname].gce_public_ip }} private ip:{{ hostvars[inventory_hostname].gce_private_ip }}"
+ msg: "private ip:{{ hostvars[inventory_hostname].gce_private_ip }}"
diff --git a/playbooks/gce/openshift-cluster/tasks/launch_instances.yml b/playbooks/gce/openshift-cluster/tasks/launch_instances.yml
index 6307ecc27..c428cb465 100644
--- a/playbooks/gce/openshift-cluster/tasks/launch_instances.yml
+++ b/playbooks/gce/openshift-cluster/tasks/launch_instances.yml
@@ -10,14 +10,33 @@
service_account_email: "{{ lookup('env', 'gce_service_account_email_address') }}"
pem_file: "{{ lookup('env', 'gce_service_account_pem_file_path') }}"
project_id: "{{ lookup('env', 'gce_project_id') }}"
+ zone: "{{ lookup('env', 'zone') }}"
+ network: "{{ lookup('env', 'network') }}"
+# unsupported in 1.9.+
+ #service_account_permissions: "datastore,logging-write"
tags:
- created-by-{{ lookup('env', 'LOGNAME') |default(cluster, true) }}
- env-{{ cluster }}
- host-type-{{ type }}
- - sub-host-type-{{ sub_host_type }}
+ - sub-host-type-{{ g_sub_host_type }}
- env-host-type-{{ cluster }}-openshift-{{ type }}
+ when: instances |length > 0
register: gce
+- set_fact:
+ node_label:
+ # There doesn't seem to be a way to get the region directly, so parse it out of the zone.
+ region: "{{ gce.zone | regex_replace('^(.*)-.*$', '\\\\1') }}"
+ type: "{{ g_sub_host_type }}"
+ when: instances |length > 0 and type == "node"
+
+- set_fact:
+ node_label:
+ # There doesn't seem to be a way to get the region directly, so parse it out of the zone.
+ region: "{{ gce.zone | regex_replace('^(.*)-.*$', '\\\\1') }}"
+ type: "{{ type }}"
+ when: instances |length > 0 and type != "node"
+
- name: Add new instances to groups and set variables needed
add_host:
hostname: "{{ item.name }}"
@@ -27,16 +46,17 @@
groups: "{{ item.tags | oo_prepend_strings_in_list('tag_') | join(',') }}"
gce_public_ip: "{{ item.public_ip }}"
gce_private_ip: "{{ item.private_ip }}"
- with_items: gce.instance_data
+ openshift_node_labels: "{{ node_label }}"
+ with_items: gce.instance_data | default([], true)
- name: Wait for ssh
wait_for: port=22 host={{ item.public_ip }}
- with_items: gce.instance_data
+ with_items: gce.instance_data | default([], true)
- name: Wait for user setup
command: "ssh -o StrictHostKeyChecking=no -o PasswordAuthentication=no -o ConnectTimeout=10 -o UserKnownHostsFile=/dev/null {{ hostvars[item.name].ansible_ssh_user }}@{{ item.public_ip }} echo {{ hostvars[item.name].ansible_ssh_user }} user is setup"
register: result
until: result.rc == 0
- retries: 20
- delay: 10
- with_items: gce.instance_data
+ retries: 30
+ delay: 5
+ with_items: gce.instance_data | default([], true)
diff --git a/playbooks/gce/openshift-cluster/terminate.yml b/playbooks/gce/openshift-cluster/terminate.yml
index 098b0df73..e20e0a8bc 100644
--- a/playbooks/gce/openshift-cluster/terminate.yml
+++ b/playbooks/gce/openshift-cluster/terminate.yml
@@ -1,25 +1,18 @@
---
- name: Terminate instance(s)
hosts: localhost
+ connection: local
gather_facts: no
vars_files:
- vars.yml
tasks:
- - set_fact: scratch_group=tag_env-host-type-{{ cluster_id }}-openshift-node
+ - set_fact: scratch_group=tag_env-{{ cluster_id }}
- add_host:
name: "{{ item }}"
- groups: oo_hosts_to_terminate, oo_nodes_to_terminate
+ groups: oo_hosts_to_terminate
ansible_ssh_user: "{{ deployment_vars[deployment_type].ssh_user | default(ansible_ssh_user, true) }}"
ansible_sudo: "{{ deployment_vars[deployment_type].sudo }}"
- with_items: groups[scratch_group] | default([]) | difference(['localhost']) | difference(groups.status_terminated)
-
- - set_fact: scratch_group=tag_env-host-type-{{ cluster_id }}-openshift-master
- - add_host:
- name: "{{ item }}"
- groups: oo_hosts_to_terminate, oo_masters_to_terminate
- ansible_ssh_user: "{{ deployment_vars[deployment_type].ssh_user | default(ansible_ssh_user, true) }}"
- ansible_sudo: "{{ deployment_vars[deployment_type].sudo }}"
- with_items: groups[scratch_group] | default([]) | difference(['localhost']) | difference(groups.status_terminated)
+ with_items: groups[scratch_group] | default([], true) | difference(['localhost']) | difference(groups.status_terminated | default([], true))
- name: Unsubscribe VMs
hosts: oo_hosts_to_terminate
@@ -32,14 +25,34 @@
lookup('oo_option', 'rhel_skip_subscription') | default(rhsub_skip, True) |
default('no', True) | lower in ['no', 'false']
-- include: ../openshift-node/terminate.yml
- vars:
- gce_service_account_email: "{{ lookup('env', 'gce_service_account_email_address') }}"
- gce_pem_file: "{{ lookup('env', 'gce_service_account_pem_file_path') }}"
- gce_project_id: "{{ lookup('env', 'gce_project_id') }}"
+- name: Terminate instances(s)
+ hosts: localhost
+ connection: local
+ gather_facts: no
+ vars_files:
+ - vars.yml
+ tasks:
+
+ - name: Terminate instances that were previously launched
+ local_action:
+ module: gce
+ state: 'absent'
+ name: "{{ item }}"
+ service_account_email: "{{ lookup('env', 'gce_service_account_email_address') }}"
+ pem_file: "{{ lookup('env', 'gce_service_account_pem_file_path') }}"
+ project_id: "{{ lookup('env', 'gce_project_id') }}"
+ zone: "{{ lookup('env', 'zone') }}"
+ with_items: groups['oo_hosts_to_terminate'] | default([], true)
+ when: item is defined
-- include: ../openshift-master/terminate.yml
- vars:
- gce_service_account_email: "{{ lookup('env', 'gce_service_account_email_address') }}"
- gce_pem_file: "{{ lookup('env', 'gce_service_account_pem_file_path') }}"
- gce_project_id: "{{ lookup('env', 'gce_project_id') }}"
+#- include: ../openshift-node/terminate.yml
+# vars:
+# gce_service_account_email: "{{ lookup('env', 'gce_service_account_email_address') }}"
+# gce_pem_file: "{{ lookup('env', 'gce_service_account_pem_file_path') }}"
+# gce_project_id: "{{ lookup('env', 'gce_project_id') }}"
+#
+#- include: ../openshift-master/terminate.yml
+# vars:
+# gce_service_account_email: "{{ lookup('env', 'gce_service_account_email_address') }}"
+# gce_pem_file: "{{ lookup('env', 'gce_service_account_pem_file_path') }}"
+# gce_project_id: "{{ lookup('env', 'gce_project_id') }}"
diff --git a/playbooks/gce/openshift-cluster/vars.yml b/playbooks/gce/openshift-cluster/vars.yml
index ae33083b9..6de007807 100644
--- a/playbooks/gce/openshift-cluster/vars.yml
+++ b/playbooks/gce/openshift-cluster/vars.yml
@@ -1,8 +1,11 @@
---
+do_we_use_openshift_sdn: true
+sdn_network_plugin: redhat/openshift-ovs-subnet
+# os_sdn_network_plugin_name can be ovssubnet or multitenant, see https://docs.openshift.org/latest/architecture/additional_concepts/sdn.html#ovssubnet-plugin-operation
deployment_vars:
origin:
- image: centos-7
- ssh_user:
+ image: preinstalled-slave-50g-v5
+ ssh_user: root
sudo: yes
online:
image: libra-rhel7
@@ -12,4 +15,3 @@ deployment_vars:
image: rhel-7
ssh_user:
sudo: yes
-
diff --git a/playbooks/libvirt/openshift-cluster/tasks/launch_instances.yml b/playbooks/libvirt/openshift-cluster/tasks/launch_instances.yml
index 2a0c90b46..4b91c6da8 100644
--- a/playbooks/libvirt/openshift-cluster/tasks/launch_instances.yml
+++ b/playbooks/libvirt/openshift-cluster/tasks/launch_instances.yml
@@ -64,7 +64,7 @@
register: nb_allocated_ips
until: nb_allocated_ips.stdout == '{{ instances | length }}'
retries: 60
- delay: 1
+ delay: 3
when: instances | length != 0
- name: Collect IP addresses of the VMs
diff --git a/playbooks/libvirt/openshift-cluster/templates/network.xml b/playbooks/libvirt/openshift-cluster/templates/network.xml
index 86dcd62bb..050bc7ab9 100644
--- a/playbooks/libvirt/openshift-cluster/templates/network.xml
+++ b/playbooks/libvirt/openshift-cluster/templates/network.xml
@@ -8,7 +8,7 @@
<!-- TODO: query for first available virbr interface available -->
<bridge name='virbr3' stp='on' delay='0'/>
<!-- TODO: make overridable -->
- <domain name='example.com'/>
+ <domain name='example.com' localOnly='yes' />
<dns>
<!-- TODO: automatically add host entries -->
</dns>
diff --git a/playbooks/libvirt/openshift-cluster/templates/user-data b/playbooks/libvirt/openshift-cluster/templates/user-data
index 77b788109..eacae7c7e 100644
--- a/playbooks/libvirt/openshift-cluster/templates/user-data
+++ b/playbooks/libvirt/openshift-cluster/templates/user-data
@@ -19,5 +19,5 @@ system_info:
ssh_authorized_keys:
- {{ lookup('file', '~/.ssh/id_rsa.pub') }}
-bootcmd:
+runcmd:
- NETWORK_CONFIG=/etc/sysconfig/network-scripts/ifcfg-eth0; if ! grep DHCP_HOSTNAME ${NETWORK_CONFIG}; then echo 'DHCP_HOSTNAME="{{ item[0] }}.example.com"' >> ${NETWORK_CONFIG}; fi; pkill -9 dhclient; service network restart
diff --git a/roles/ansible_tower/tasks/main.yaml b/roles/ansible_tower/tasks/main.yaml
index c110a3b70..b7757214d 100644
--- a/roles/ansible_tower/tasks/main.yaml
+++ b/roles/ansible_tower/tasks/main.yaml
@@ -9,6 +9,7 @@
- ansible
- telnet
- ack
+ - pylint
- name: download Tower setup
get_url: url=http://releases.ansible.com/ansible-tower/setup/ansible-tower-setup-2.1.1.tar.gz dest=/opt/ force=no
@@ -38,5 +39,3 @@
regexp: "^({{ item.option }})( *)="
line: '\1\2= {{ item.value }}'
with_items: config_changes | default([], true)
-
-
diff --git a/roles/etcd/tasks/main.yml b/roles/etcd/tasks/main.yml
index 27bfb7de9..656901409 100644
--- a/roles/etcd/tasks/main.yml
+++ b/roles/etcd/tasks/main.yml
@@ -38,6 +38,7 @@
template:
src: etcd.conf.j2
dest: /etc/etcd/etcd.conf
+ backup: true
notify:
- restart etcd
diff --git a/roles/etcd_ca/tasks/main.yml b/roles/etcd_ca/tasks/main.yml
index 8a266f732..625756867 100644
--- a/roles/etcd_ca/tasks/main.yml
+++ b/roles/etcd_ca/tasks/main.yml
@@ -18,6 +18,7 @@
- template:
dest: "{{ etcd_ca_dir }}/fragments/openssl_append.cnf"
src: openssl_append.j2
+ backup: true
- assemble:
src: "{{ etcd_ca_dir }}/fragments"
diff --git a/roles/fluentd_master/tasks/main.yml b/roles/fluentd_master/tasks/main.yml
index 69f8eceab..55cd94460 100644
--- a/roles/fluentd_master/tasks/main.yml
+++ b/roles/fluentd_master/tasks/main.yml
@@ -52,4 +52,3 @@
name: 'td-agent'
state: started
enabled: yes
-
diff --git a/roles/lib_zabbix/library/zbx_action.py b/roles/lib_zabbix/library/zbx_action.py
new file mode 100644
index 000000000..d64cebae1
--- /dev/null
+++ b/roles/lib_zabbix/library/zbx_action.py
@@ -0,0 +1,538 @@
+#!/usr/bin/env python
+'''
+ Ansible module for zabbix actions
+'''
+# vim: expandtab:tabstop=4:shiftwidth=4
+#
+# Zabbix action ansible module
+#
+#
+# Copyright 2015 Red Hat Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# This is in place because each module looks similar to each other.
+# These need duplicate code as their behavior is very similar
+# but different for each zabbix class.
+# pylint: disable=duplicate-code
+
+# pylint: disable=import-error
+from openshift_tools.monitoring.zbxapi import ZabbixAPI, ZabbixConnection, ZabbixAPIError
+
+def exists(content, key='result'):
+ ''' Check if key exists in content or the size of content[key] > 0
+ '''
+ if not content.has_key(key):
+ return False
+
+ if not content[key]:
+ return False
+
+ return True
+
+def conditions_equal(zab_conditions, user_conditions):
+ '''Compare two lists of conditions'''
+ c_type = 'conditiontype'
+ _op = 'operator'
+ val = 'value'
+ if len(user_conditions) != len(zab_conditions):
+ return False
+
+ for zab_cond, user_cond in zip(zab_conditions, user_conditions):
+ if zab_cond[c_type] != str(user_cond[c_type]) or zab_cond[_op] != str(user_cond[_op]) or \
+ zab_cond[val] != str(user_cond[val]):
+ return False
+
+ return True
+
+def filter_differences(zabbix_filters, user_filters):
+ '''Determine the differences from user and zabbix for operations'''
+ rval = {}
+ for key, val in user_filters.items():
+
+ if key == 'conditions':
+ if not conditions_equal(zabbix_filters[key], val):
+ rval[key] = val
+
+ elif zabbix_filters[key] != str(val):
+ rval[key] = val
+
+ return rval
+
+# 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
+def operation_differences(zabbix_ops, user_ops):
+ '''Determine the differences from user and zabbix for operations'''
+
+ # if they don't match, take the user options
+ if len(zabbix_ops) != len(user_ops):
+ return user_ops
+
+ rval = {}
+ for zab, user in zip(zabbix_ops, user_ops):
+ for key, val in user.items():
+ if key == 'opconditions':
+ 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 zab[key] != str(val):
+ rval[key] = val
+ return rval
+
+def get_users(zapi, users):
+ '''get the mediatype id from the mediatype name'''
+ rval_users = []
+
+ for user in users:
+ content = zapi.get_content('user',
+ 'get',
+ {'filter': {'alias': user}})
+ rval_users.append({'userid': content['result'][0]['userid']})
+
+ return rval_users
+
+def get_user_groups(zapi, groups):
+ '''get the mediatype id from the mediatype name'''
+ user_groups = []
+
+ content = zapi.get_content('usergroup',
+ 'get',
+ {'search': {'name': groups}})
+
+ for usr_grp in content['result']:
+ user_groups.append({'usrgrpid': usr_grp['usrgrpid']})
+
+ return user_groups
+
+def get_mediatype_id_by_name(zapi, m_name):
+ '''get the mediatype id from the mediatype name'''
+ content = zapi.get_content('mediatype',
+ 'get',
+ {'filter': {'description': m_name}})
+
+ return content['result'][0]['mediatypeid']
+
+def get_priority(priority):
+ ''' determine priority
+ '''
+ prior = 0
+ if 'info' in priority:
+ prior = 1
+ elif 'warn' in priority:
+ prior = 2
+ elif 'avg' == priority or 'ave' in priority:
+ prior = 3
+ elif 'high' in priority:
+ prior = 4
+ elif 'dis' in priority:
+ prior = 5
+
+ return prior
+
+def get_event_source(from_src):
+ '''Translate even str into value'''
+ choices = ['trigger', 'discovery', 'auto', 'internal']
+ rval = 0
+ try:
+ rval = choices.index(from_src)
+ except ValueError as _:
+ ZabbixAPIError('Value not found for event source [%s]' % from_src)
+
+ return rval
+
+def get_status(inc_status):
+ '''determine status for action'''
+ rval = 1
+ if inc_status == 'enabled':
+ rval = 0
+
+ return rval
+
+def get_condition_operator(inc_operator):
+ ''' determine the condition operator'''
+ vals = {'=': 0,
+ '<>': 1,
+ 'like': 2,
+ 'not like': 3,
+ 'in': 4,
+ '>=': 5,
+ '<=': 6,
+ 'not in': 7,
+ }
+
+ return vals[inc_operator]
+
+def get_host_id_by_name(zapi, host_name):
+ '''Get host id by name'''
+ content = zapi.get_content('host',
+ 'get',
+ {'filter': {'name': host_name}})
+
+ return content['result'][0]['hostid']
+
+def get_trigger_value(inc_trigger):
+ '''determine the proper trigger value'''
+ rval = 1
+ if inc_trigger == 'PROBLEM':
+ rval = 1
+ else:
+ rval = 0
+
+ return rval
+
+def get_template_id_by_name(zapi, t_name):
+ '''get the template id by name'''
+ content = zapi.get_content('template',
+ 'get',
+ {'filter': {'host': t_name}})
+
+ return content['result'][0]['templateid']
+
+
+def get_host_group_id_by_name(zapi, hg_name):
+ '''Get hostgroup id by name'''
+ content = zapi.get_content('hostgroup',
+ 'get',
+ {'filter': {'name': hg_name}})
+
+ return content['result'][0]['groupid']
+
+def get_condition_type(event_source, inc_condition):
+ '''determine the condition type'''
+ c_types = {}
+ if event_source == 'trigger':
+ c_types = {'host group': 0,
+ 'host': 1,
+ 'trigger': 2,
+ 'trigger name': 3,
+ 'trigger severity': 4,
+ 'trigger value': 5,
+ 'time period': 6,
+ 'host template': 13,
+ 'application': 15,
+ 'maintenance status': 16,
+ }
+
+ elif event_source == 'discovery':
+ c_types = {'host IP': 7,
+ 'discovered service type': 8,
+ 'discovered service port': 9,
+ 'discovery status': 10,
+ 'uptime or downtime duration': 11,
+ 'received value': 12,
+ 'discovery rule': 18,
+ 'discovery check': 19,
+ 'proxy': 20,
+ 'discovery object': 21,
+ }
+
+ elif event_source == 'auto':
+ c_types = {'proxy': 20,
+ 'host name': 22,
+ 'host metadata': 24,
+ }
+
+ elif event_source == 'internal':
+ c_types = {'host group': 0,
+ 'host': 1,
+ 'host template': 13,
+ 'application': 15,
+ 'event type': 23,
+ }
+ else:
+ raise ZabbixAPIError('Unkown event source %s' % event_source)
+
+ return c_types[inc_condition]
+
+def get_operation_type(inc_operation):
+ ''' determine the correct operation type'''
+ o_types = {'send message': 0,
+ 'remote command': 1,
+ 'add host': 2,
+ 'remove host': 3,
+ 'add to host group': 4,
+ 'remove from host group': 5,
+ 'link to template': 6,
+ 'unlink from template': 7,
+ 'enable host': 8,
+ 'disable host': 9,
+ }
+
+ return o_types[inc_operation]
+
+def get_action_operations(zapi, inc_operations):
+ '''Convert the operations into syntax for api'''
+ for operation in inc_operations:
+ operation['operationtype'] = get_operation_type(operation['operationtype'])
+ if operation['operationtype'] == 0: # send message. Need to fix the
+ operation['opmessage']['mediatypeid'] = \
+ get_mediatype_id_by_name(zapi, operation['opmessage']['mediatypeid'])
+ operation['opmessage_grp'] = get_user_groups(zapi, operation.get('opmessage_grp', []))
+ operation['opmessage_usr'] = get_users(zapi, operation.get('opmessage_usr', []))
+ if operation['opmessage']['default_msg']:
+ operation['opmessage']['default_msg'] = 1
+ else:
+ operation['opmessage']['default_msg'] = 0
+
+ # NOT supported for remote commands
+ elif operation['operationtype'] == 1:
+ continue
+
+ # Handle Operation conditions:
+ # Currently there is only 1 available which
+ # is 'event acknowledged'. In the future
+ # if there are any added we will need to pass this
+ # option to a function and return the correct conditiontype
+ if operation.has_key('opconditions'):
+ for condition in operation['opconditions']:
+ if condition['conditiontype'] == 'event acknowledged':
+ condition['conditiontype'] = 14
+
+ if condition['operator'] == '=':
+ condition['operator'] = 0
+
+ if condition['value'] == 'acknowledged':
+ condition['operator'] = 1
+ else:
+ condition['operator'] = 0
+
+
+ return inc_operations
+
+def get_operation_evaltype(inc_type):
+ '''get the operation evaltype'''
+ rval = 0
+ if inc_type == 'and/or':
+ rval = 0
+ elif inc_type == 'and':
+ rval = 1
+ elif inc_type == 'or':
+ rval = 2
+ elif inc_type == 'custom':
+ rval = 3
+
+ return rval
+
+def get_action_conditions(zapi, event_source, inc_conditions):
+ '''Convert the conditions into syntax for api'''
+
+ calc_type = inc_conditions.pop('calculation_type')
+ inc_conditions['evaltype'] = get_operation_evaltype(calc_type)
+ for cond in inc_conditions['conditions']:
+
+ cond['operator'] = get_condition_operator(cond['operator'])
+ # Based on conditiontype we need to set the proper value
+ # e.g. conditiontype = hostgroup then the value needs to be a hostgroup id
+ # e.g. conditiontype = host the value needs to be a host id
+ cond['conditiontype'] = get_condition_type(event_source, cond['conditiontype'])
+ if cond['conditiontype'] == 0:
+ cond['value'] = get_host_group_id_by_name(zapi, cond['value'])
+ elif cond['conditiontype'] == 1:
+ cond['value'] = get_host_id_by_name(zapi, cond['value'])
+ elif cond['conditiontype'] == 4:
+ cond['value'] = get_priority(cond['value'])
+
+ elif cond['conditiontype'] == 5:
+ cond['value'] = get_trigger_value(cond['value'])
+ elif cond['conditiontype'] == 13:
+ cond['value'] = get_template_id_by_name(zapi, cond['value'])
+ elif cond['conditiontype'] == 16:
+ cond['value'] = ''
+
+ return inc_conditions
+
+
+def get_send_recovery(send_recovery):
+ '''Get the integer value'''
+ rval = 0
+ if send_recovery:
+ rval = 1
+
+ return rval
+
+# The branches are needed for CRUD and error handling
+# pylint: disable=too-many-branches
+def main():
+ '''
+ ansible zabbix module for zbx_item
+ '''
+
+
+ module = AnsibleModule(
+ argument_spec=dict(
+ zbx_server=dict(default='https://localhost/zabbix/api_jsonrpc.php', type='str'),
+ zbx_user=dict(default=os.environ.get('ZABBIX_USER', None), type='str'),
+ zbx_password=dict(default=os.environ.get('ZABBIX_PASSWORD', None), type='str'),
+ zbx_debug=dict(default=False, type='bool'),
+
+ name=dict(default=None, type='str'),
+ event_source=dict(default='trigger', choices=['trigger', 'discovery', 'auto', 'internal'], type='str'),
+ action_subject=dict(default="{TRIGGER.NAME}: {TRIGGER.STATUS}", type='str'),
+ action_message=dict(default="{TRIGGER.NAME}: {TRIGGER.STATUS}\r\n" +
+ "Last value: {ITEM.LASTVALUE}\r\n\r\n{TRIGGER.URL}", type='str'),
+ reply_subject=dict(default="{TRIGGER.NAME}: {TRIGGER.STATUS}", type='str'),
+ reply_message=dict(default="Trigger: {TRIGGER.NAME}\r\nTrigger status: {TRIGGER.STATUS}\r\n" +
+ "Trigger severity: {TRIGGER.SEVERITY}\r\nTrigger URL: {TRIGGER.URL}\r\n\r\n" +
+ "Item values:\r\n\r\n1. {ITEM.NAME1} ({HOST.NAME1}:{ITEM.KEY1}): " +
+ "{ITEM.VALUE1}\r\n2. {ITEM.NAME2} ({HOST.NAME2}:{ITEM.KEY2}): " +
+ "{ITEM.VALUE2}\r\n3. {ITEM.NAME3} ({HOST.NAME3}:{ITEM.KEY3}): " +
+ "{ITEM.VALUE3}", type='str'),
+ send_recovery=dict(default=False, type='bool'),
+ status=dict(default=None, type='str'),
+ escalation_time=dict(default=60, type='int'),
+ conditions_filter=dict(default=None, type='dict'),
+ operations=dict(default=None, type='list'),
+ state=dict(default='present', type='str'),
+ ),
+ #supports_check_mode=True
+ )
+
+ zapi = ZabbixAPI(ZabbixConnection(module.params['zbx_server'],
+ module.params['zbx_user'],
+ module.params['zbx_password'],
+ module.params['zbx_debug']))
+
+ #Set the instance and the template for the rest of the calls
+ zbx_class_name = 'action'
+ state = module.params['state']
+
+ content = zapi.get_content(zbx_class_name,
+ 'get',
+ {'search': {'name': module.params['name']},
+ 'selectFilter': 'extend',
+ 'selectOperations': 'extend',
+ })
+
+ #******#
+ # GET
+ #******#
+ if state == 'list':
+ module.exit_json(changed=False, results=content['result'], state="list")
+
+ #******#
+ # DELETE
+ #******#
+ if state == 'absent':
+ if not exists(content):
+ module.exit_json(changed=False, state="absent")
+
+ content = zapi.get_content(zbx_class_name, 'delete', [content['result'][0]['itemid']])
+ module.exit_json(changed=True, results=content['result'], state="absent")
+
+ # Create and Update
+ if state == 'present':
+
+ conditions = get_action_conditions(zapi, module.params['event_source'], module.params['conditions_filter'])
+ operations = get_action_operations(zapi, module.params['operations'])
+ params = {'name': module.params['name'],
+ 'esc_period': module.params['escalation_time'],
+ 'eventsource': get_event_source(module.params['event_source']),
+ 'status': get_status(module.params['status']),
+ 'def_shortdata': module.params['action_subject'],
+ 'def_longdata': module.params['action_message'],
+ 'r_shortdata': module.params['reply_subject'],
+ 'r_longdata': module.params['reply_message'],
+ 'recovery_msg': get_send_recovery(module.params['send_recovery']),
+ 'filter': conditions,
+ 'operations': operations,
+ }
+
+ # Remove any None valued params
+ _ = [params.pop(key, None) for key in params.keys() if params[key] is None]
+
+ #******#
+ # CREATE
+ #******#
+ if not exists(content):
+ content = zapi.get_content(zbx_class_name, 'create', params)
+
+ if content.has_key('error'):
+ module.exit_json(failed=True, changed=True, results=content['error'], state="present")
+
+ module.exit_json(changed=True, results=content['result'], state='present')
+
+
+ ########
+ # UPDATE
+ ########
+ _ = params.pop('hostid', None)
+ differences = {}
+ zab_results = content['result'][0]
+ for key, value in params.items():
+
+ if key == 'operations':
+ ops = operation_differences(zab_results[key], value)
+ if ops:
+ differences[key] = ops
+
+ elif key == 'filter':
+ filters = filter_differences(zab_results[key], value)
+ if filters:
+ differences[key] = filters
+
+ elif zab_results[key] != value and zab_results[key] != str(value):
+ differences[key] = value
+
+ if not differences:
+ module.exit_json(changed=False, results=zab_results, state="present")
+
+ # We have differences and need to update.
+ # action update requires an id, filters, and operations
+ differences['actionid'] = zab_results['actionid']
+ differences['operations'] = params['operations']
+ differences['filter'] = params['filter']
+ content = zapi.get_content(zbx_class_name, 'update', differences)
+
+ if content.has_key('error'):
+ module.exit_json(failed=True, changed=False, results=content['error'], state="present")
+
+ module.exit_json(changed=True, results=content['result'], state="present")
+
+ module.exit_json(failed=True,
+ changed=False,
+ results='Unknown state passed. %s' % state,
+ state="unknown")
+
+# pylint: disable=redefined-builtin, unused-wildcard-import, wildcard-import, locally-disabled
+# import module snippets. This are required
+from ansible.module_utils.basic import *
+
+main()
diff --git a/roles/lib_zabbix/library/zbx_discoveryrule.py b/roles/lib_zabbix/library/zbx_discoveryrule.py
index 71a0580c2..f52f350a5 100644
--- a/roles/lib_zabbix/library/zbx_discoveryrule.py
+++ b/roles/lib_zabbix/library/zbx_discoveryrule.py
@@ -85,6 +85,7 @@ def main():
Ansible module for zabbix discovery rules
'''
+
module = AnsibleModule(
argument_spec=dict(
zbx_server=dict(default='https://localhost/zabbix/api_jsonrpc.php', type='str'),
@@ -93,6 +94,7 @@ def main():
zbx_debug=dict(default=False, type='bool'),
name=dict(default=None, type='str'),
key=dict(default=None, type='str'),
+ description=dict(default=None, type='str'),
interfaceid=dict(default=None, type='int'),
ztype=dict(default='trapper', type='str'),
delay=dict(default=60, type='int'),
@@ -113,18 +115,27 @@ def main():
idname = "itemid"
dname = module.params['name']
state = module.params['state']
+ template = get_template(zapi, module.params['template_name'])
# selectInterfaces doesn't appear to be working but is needed.
content = zapi.get_content(zbx_class_name,
'get',
{'search': {'name': dname},
+ 'templateids': template['templateid'],
#'selectDServices': 'extend',
#'selectDChecks': 'extend',
#'selectDhosts': 'dhostid',
})
+
+ #******#
+ # GET
+ #******#
if state == 'list':
module.exit_json(changed=False, results=content['result'], state="list")
+ #******#
+ # DELETE
+ #******#
if state == 'absent':
if not exists(content):
module.exit_json(changed=False, state="absent")
@@ -132,24 +143,37 @@ def main():
content = zapi.get_content(zbx_class_name, 'delete', [content['result'][0][idname]])
module.exit_json(changed=True, results=content['result'], state="absent")
+
+ # Create and Update
if state == 'present':
- template = get_template(zapi, module.params['template_name'])
params = {'name': dname,
'key_': module.params['key'],
'hostid': template['templateid'],
'interfaceid': module.params['interfaceid'],
'lifetime': module.params['lifetime'],
'type': get_type(module.params['ztype']),
+ 'description': module.params['description'],
}
if params['type'] in [2, 5, 7, 11]:
params.pop('interfaceid')
+ # Remove any None valued params
+ _ = [params.pop(key, None) for key in params.keys() if params[key] is None]
+
+ #******#
+ # CREATE
+ #******#
if not exists(content):
- # if we didn't find it, create it
content = zapi.get_content(zbx_class_name, 'create', params)
+
+ if content.has_key('error'):
+ module.exit_json(failed=True, changed=True, results=content['error'], state="present")
+
module.exit_json(changed=True, results=content['result'], state='present')
- # already exists, we need to update it
- # let's compare properties
+
+ ########
+ # UPDATE
+ ########
differences = {}
zab_results = content['result'][0]
for key, value in params.items():
@@ -163,6 +187,10 @@ def main():
# We have differences and need to update
differences[idname] = zab_results[idname]
content = zapi.get_content(zbx_class_name, 'update', differences)
+
+ if content.has_key('error'):
+ module.exit_json(failed=True, changed=False, results=content['error'], state="present")
+
module.exit_json(changed=True, results=content['result'], state="present")
module.exit_json(failed=True,
diff --git a/roles/lib_zabbix/library/zbx_item.py b/roles/lib_zabbix/library/zbx_item.py
index 2ccc21292..6faa82dfc 100644
--- a/roles/lib_zabbix/library/zbx_item.py
+++ b/roles/lib_zabbix/library/zbx_item.py
@@ -53,6 +53,8 @@ def get_value_type(value_type):
vtype = 0
if 'int' in value_type:
vtype = 3
+ elif 'log' in value_type:
+ vtype = 2
elif 'char' in value_type:
vtype = 1
elif 'str' in value_type:
diff --git a/roles/lib_zabbix/library/zbx_itemprototype.py b/roles/lib_zabbix/library/zbx_itemprototype.py
index 24f85710d..e7fd6fa21 100644
--- a/roles/lib_zabbix/library/zbx_itemprototype.py
+++ b/roles/lib_zabbix/library/zbx_itemprototype.py
@@ -38,13 +38,14 @@ def exists(content, key='result'):
return True
-def get_rule_id(zapi, discoveryrule_name):
+def get_rule_id(zapi, discoveryrule_key, templateid):
'''get a discoveryrule by name
'''
content = zapi.get_content('discoveryrule',
'get',
- {'search': {'name': discoveryrule_name},
+ {'search': {'key_': discoveryrule_key},
'output': 'extend',
+ 'templateids': templateid,
})
if not content['result']:
return None
@@ -53,6 +54,9 @@ def get_rule_id(zapi, discoveryrule_name):
def get_template(zapi, template_name):
'''get a template by name
'''
+ if not template_name:
+ return None
+
content = zapi.get_content('template',
'get',
{'search': {'host': template_name},
@@ -124,16 +128,17 @@ def get_status(status):
return _status
-def get_app_ids(zapi, application_names):
+def get_app_ids(zapi, application_names, templateid):
''' get application ids from names
'''
app_ids = []
for app_name in application_names:
- content = zapi.get_content('application', 'get', {'search': {'name': app_name}})
+ content = zapi.get_content('application', 'get', {'filter': {'name': app_name}, 'templateids': templateid})
if content.has_key('result'):
app_ids.append(content['result'][0]['applicationid'])
return app_ids
+# pylint: disable=too-many-branches
def main():
'''
Ansible module for zabbix discovery rules
@@ -147,16 +152,17 @@ def main():
zbx_debug=dict(default=False, type='bool'),
name=dict(default=None, type='str'),
key=dict(default=None, type='str'),
+ description=dict(default=None, type='str'),
interfaceid=dict(default=None, type='int'),
ztype=dict(default='trapper', type='str'),
value_type=dict(default='float', type='str'),
delay=dict(default=60, type='int'),
lifetime=dict(default=30, type='int'),
- template_name=dict(default=[], type='list'),
state=dict(default='present', type='str'),
status=dict(default='enabled', type='str'),
- discoveryrule_name=dict(default=None, type='str'),
applications=dict(default=[], type='list'),
+ template_name=dict(default=None, type='str'),
+ discoveryrule_key=dict(default=None, type='str'),
),
#supports_check_mode=True
)
@@ -169,20 +175,27 @@ def main():
#Set the instance and the template for the rest of the calls
zbx_class_name = 'itemprototype'
idname = "itemid"
- dname = module.params['name']
state = module.params['state']
+ template = get_template(zapi, module.params['template_name'])
# selectInterfaces doesn't appear to be working but is needed.
content = zapi.get_content(zbx_class_name,
'get',
- {'search': {'name': dname},
+ {'search': {'key_': module.params['key']},
'selectApplications': 'applicationid',
'selectDiscoveryRule': 'itemid',
- #'selectDhosts': 'dhostid',
+ 'templated': True,
})
+
+ #******#
+ # GET
+ #******#
if state == 'list':
module.exit_json(changed=False, results=content['result'], state="list")
+ #******#
+ # DELETE
+ #******#
if state == 'absent':
if not exists(content):
module.exit_json(changed=False, state="absent")
@@ -190,26 +203,39 @@ def main():
content = zapi.get_content(zbx_class_name, 'delete', [content['result'][0][idname]])
module.exit_json(changed=True, results=content['result'], state="absent")
+ # Create and Update
if state == 'present':
- template = get_template(zapi, module.params['template_name'])
- params = {'name': dname,
+ params = {'name': module.params['name'],
'key_': module.params['key'],
'hostid': template['templateid'],
'interfaceid': module.params['interfaceid'],
- 'ruleid': get_rule_id(zapi, module.params['discoveryrule_name']),
+ 'ruleid': get_rule_id(zapi, module.params['discoveryrule_key'], template['templateid']),
'type': get_type(module.params['ztype']),
'value_type': get_value_type(module.params['value_type']),
- 'applications': get_app_ids(zapi, module.params['applications']),
+ 'applications': get_app_ids(zapi, module.params['applications'], template['templateid']),
+ 'description': module.params['description'],
}
+
if params['type'] in [2, 5, 7, 8, 11, 15]:
params.pop('interfaceid')
+ # Remove any None valued params
+ _ = [params.pop(key, None) for key in params.keys() if params[key] is None]
+
+ #******#
+ # CREATE
+ #******#
if not exists(content):
- # if we didn't find it, create it
content = zapi.get_content(zbx_class_name, 'create', params)
+
+ if content.has_key('error'):
+ module.exit_json(failed=True, changed=False, results=content['error'], state="present")
+
module.exit_json(changed=True, results=content['result'], state='present')
- # already exists, we need to update it
- # let's compare properties
+
+ #******#
+ # UPDATE
+ #******#
differences = {}
zab_results = content['result'][0]
for key, value in params.items():
@@ -218,6 +244,11 @@ def main():
if value != zab_results['discoveryRule']['itemid']:
differences[key] = value
+ elif key == 'applications':
+ app_ids = [app['applicationid'] for app in zab_results[key]]
+ if set(app_ids) - set(value):
+ differences[key] = value
+
elif zab_results[key] != value and zab_results[key] != str(value):
differences[key] = value
@@ -227,6 +258,10 @@ def main():
# We have differences and need to update
differences[idname] = zab_results[idname]
content = zapi.get_content(zbx_class_name, 'update', differences)
+
+ if content.has_key('error'):
+ module.exit_json(failed=True, changed=False, results=content['error'], state="present")
+
module.exit_json(changed=True, results=content['result'], state="present")
module.exit_json(failed=True,
diff --git a/roles/lib_zabbix/library/zbx_trigger.py b/roles/lib_zabbix/library/zbx_trigger.py
index a05de7e68..ab7731faa 100644
--- a/roles/lib_zabbix/library/zbx_trigger.py
+++ b/roles/lib_zabbix/library/zbx_trigger.py
@@ -74,6 +74,36 @@ def get_deps(zapi, deps):
return results
+
+def get_trigger_status(inc_status):
+ ''' Determine the trigger's status
+ 0 is enabled
+ 1 is disabled
+ '''
+ r_status = 0
+ if inc_status == 'disabled':
+ r_status = 1
+
+ return r_status
+
+def get_template_id(zapi, template_name):
+ '''
+ get related templates
+ '''
+ template_ids = []
+ app_ids = {}
+ # Fetch templates by name
+ content = zapi.get_content('template',
+ 'get',
+ {'search': {'host': template_name},
+ 'selectApplications': ['applicationid', 'name']})
+ if content.has_key('result'):
+ template_ids.append(content['result'][0]['templateid'])
+ for app in content['result'][0]['applications']:
+ app_ids[app['name']] = app['applicationid']
+
+ return template_ids, app_ids
+
def main():
'''
Create a trigger in zabbix
@@ -103,7 +133,9 @@ def main():
dependencies=dict(default=[], type='list'),
priority=dict(default='avg', type='str'),
url=dict(default=None, type='str'),
+ status=dict(default=None, type='str'),
state=dict(default='present', type='str'),
+ template_name=dict(default=None, type='str'),
),
#supports_check_mode=True
)
@@ -119,11 +151,16 @@ def main():
state = module.params['state']
tname = module.params['name']
+ templateid = None
+ if module.params['template_name']:
+ templateid, _ = get_template_id(zapi, module.params['template_name'])
+
content = zapi.get_content(zbx_class_name,
'get',
{'filter': {'description': tname},
'expandExpression': True,
'selectDependencies': 'triggerid',
+ 'templateids': templateid,
})
# Get
@@ -145,6 +182,7 @@ def main():
'dependencies': get_deps(zapi, module.params['dependencies']),
'priority': get_priority(module.params['priority']),
'url': module.params['url'],
+ 'status': get_trigger_status(module.params['status']),
}
# Remove any None valued params
@@ -156,6 +194,10 @@ def main():
if not exists(content):
# if we didn't find it, create it
content = zapi.get_content(zbx_class_name, 'create', params)
+
+ if content.has_key('error'):
+ module.exit_json(failed=True, changed=True, results=content['error'], state="present")
+
module.exit_json(changed=True, results=content['result'], state='present')
########
diff --git a/roles/lib_zabbix/library/zbx_triggerprototype.py b/roles/lib_zabbix/library/zbx_triggerprototype.py
new file mode 100644
index 000000000..c1224b268
--- /dev/null
+++ b/roles/lib_zabbix/library/zbx_triggerprototype.py
@@ -0,0 +1,177 @@
+#!/usr/bin/env python
+'''
+ansible module for zabbix triggerprototypes
+'''
+# vim: expandtab:tabstop=4:shiftwidth=4
+#
+# Zabbix triggerprototypes ansible module
+#
+#
+# Copyright 2015 Red Hat Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# This is in place because each module looks similar to each other.
+# These need duplicate code as their behavior is very similar
+# but different for each zabbix class.
+# pylint: disable=duplicate-code
+
+# pylint: disable=import-error
+from openshift_tools.monitoring.zbxapi import ZabbixAPI, ZabbixConnection
+
+def exists(content, key='result'):
+ ''' Check if key exists in content or the size of content[key] > 0
+ '''
+ if not content.has_key(key):
+ return False
+
+ if not content[key]:
+ return False
+
+ return True
+
+def get_priority(priority):
+ ''' determine priority
+ '''
+ prior = 0
+ if 'info' in priority:
+ prior = 1
+ elif 'warn' in priority:
+ prior = 2
+ elif 'avg' == priority or 'ave' in priority:
+ prior = 3
+ elif 'high' in priority:
+ prior = 4
+ elif 'dis' in priority:
+ prior = 5
+
+ return prior
+
+def get_trigger_status(inc_status):
+ ''' Determine the trigger's status
+ 0 is enabled
+ 1 is disabled
+ '''
+ r_status = 0
+ if inc_status == 'disabled':
+ r_status = 1
+
+ return r_status
+
+
+def main():
+ '''
+ Create a triggerprototype in zabbix
+ '''
+
+ module = AnsibleModule(
+ argument_spec=dict(
+ zbx_server=dict(default='https://localhost/zabbix/api_jsonrpc.php', type='str'),
+ zbx_user=dict(default=os.environ.get('ZABBIX_USER', None), type='str'),
+ zbx_password=dict(default=os.environ.get('ZABBIX_PASSWORD', None), type='str'),
+ zbx_debug=dict(default=False, type='bool'),
+ name=dict(default=None, type='str'),
+ expression=dict(default=None, type='str'),
+ description=dict(default=None, type='str'),
+ priority=dict(default='avg', type='str'),
+ url=dict(default=None, type='str'),
+ status=dict(default=None, type='str'),
+ state=dict(default='present', type='str'),
+ ),
+ #supports_check_mode=True
+ )
+
+ zapi = ZabbixAPI(ZabbixConnection(module.params['zbx_server'],
+ module.params['zbx_user'],
+ module.params['zbx_password'],
+ module.params['zbx_debug']))
+
+ #Set the instance and the template for the rest of the calls
+ zbx_class_name = 'triggerprototype'
+ idname = "triggerid"
+ state = module.params['state']
+ tname = module.params['name']
+
+ content = zapi.get_content(zbx_class_name,
+ 'get',
+ {'filter': {'description': tname},
+ 'expandExpression': True,
+ 'selectDependencies': 'triggerid',
+ })
+
+ # Get
+ if state == 'list':
+ module.exit_json(changed=False, results=content['result'], state="list")
+
+ # Delete
+ if state == 'absent':
+ if not exists(content):
+ module.exit_json(changed=False, state="absent")
+ content = zapi.get_content(zbx_class_name, 'delete', [content['result'][0][idname]])
+ module.exit_json(changed=True, results=content['result'], state="absent")
+
+ # Create and Update
+ if state == 'present':
+ params = {'description': tname,
+ 'comments': module.params['description'],
+ 'expression': module.params['expression'],
+ 'priority': get_priority(module.params['priority']),
+ 'url': module.params['url'],
+ 'status': get_trigger_status(module.params['status']),
+ }
+
+ # Remove any None valued params
+ _ = [params.pop(key, None) for key in params.keys() if params[key] is None]
+
+ #******#
+ # CREATE
+ #******#
+ if not exists(content):
+ # if we didn't find it, create it
+ content = zapi.get_content(zbx_class_name, 'create', params)
+
+ if content.has_key('error'):
+ module.exit_json(failed=True, changed=True, results=content['error'], state="present")
+
+ module.exit_json(changed=True, results=content['result'], state='present')
+
+ ########
+ # UPDATE
+ ########
+ differences = {}
+ zab_results = content['result'][0]
+ for key, value in params.items():
+
+ if zab_results[key] != value and zab_results[key] != str(value):
+ differences[key] = value
+
+ if not differences:
+ module.exit_json(changed=False, results=zab_results, state="present")
+
+ # We have differences and need to update
+ differences[idname] = zab_results[idname]
+ content = zapi.get_content(zbx_class_name, 'update', differences)
+ module.exit_json(changed=True, results=content['result'], state="present")
+
+
+ module.exit_json(failed=True,
+ changed=False,
+ results='Unknown state passed. %s' % state,
+ state="unknown")
+
+# pylint: disable=redefined-builtin, unused-wildcard-import, wildcard-import, locally-disabled
+# import module snippets. This are required
+from ansible.module_utils.basic import *
+
+main()
diff --git a/roles/lib_zabbix/library/zbx_user_media.py b/roles/lib_zabbix/library/zbx_user_media.py
index 3f7760475..8895c78c3 100644
--- a/roles/lib_zabbix/library/zbx_user_media.py
+++ b/roles/lib_zabbix/library/zbx_user_media.py
@@ -54,8 +54,8 @@ def get_mtype(zapi, mtype):
except ValueError:
pass
- content = zapi.get_content('mediatype', 'get', {'search': {'description': mtype}})
- if content.has_key['result'] and content['result']:
+ content = zapi.get_content('mediatype', 'get', {'filter': {'description': mtype}})
+ if content.has_key('result') and content['result']:
return content['result'][0]['mediatypeid']
return None
@@ -63,7 +63,7 @@ def get_mtype(zapi, mtype):
def get_user(zapi, user):
''' Get userids from user aliases
'''
- content = zapi.get_content('user', 'get', {'search': {'alias': user}})
+ content = zapi.get_content('user', 'get', {'filter': {'alias': user}})
if content['result']:
return content['result'][0]
@@ -104,15 +104,17 @@ def find_media(medias, user_media):
''' Find the user media in the list of medias
'''
for media in medias:
- if all([media[key] == user_media[key] for key in user_media.keys()]):
+ if all([media[key] == str(user_media[key]) for key in user_media.keys()]):
return media
return None
-def get_active(in_active):
+def get_active(is_active):
'''Determine active value
+ 0 - enabled
+ 1 - disabled
'''
active = 1
- if in_active:
+ if is_active:
active = 0
return active
@@ -128,6 +130,21 @@ def get_mediatype(zapi, mediatype, mediatype_desc):
return mtypeid
+def preprocess_medias(zapi, medias):
+ ''' Insert the correct information when processing medias '''
+ for media in medias:
+ # Fetch the mediatypeid from the media desc (name)
+ if media.has_key('mediatype'):
+ media['mediatypeid'] = get_mediatype(zapi, mediatype=None, mediatype_desc=media.pop('mediatype'))
+
+ media['active'] = get_active(media.get('active'))
+ media['severity'] = int(get_severity(media['severity']))
+
+ return medias
+
+# Disabling branching as the logic requires branches.
+# I've also added a few safeguards which required more branches.
+# pylint: disable=too-many-branches
def main():
'''
Ansible zabbix module for mediatype
@@ -166,11 +183,17 @@ def main():
# User media is fetched through the usermedia.get
zbx_user_query = get_zbx_user_query_data(zapi, module.params['login'])
- content = zapi.get_content('usermedia', 'get', zbx_user_query)
-
+ content = zapi.get_content('usermedia', 'get',
+ {'userids': [uid for user, uid in zbx_user_query.items()]})
+ #####
+ # Get
+ #####
if state == 'list':
module.exit_json(changed=False, results=content['result'], state="list")
+ ########
+ # Delete
+ ########
if state == 'absent':
if not exists(content) or len(content['result']) == 0:
module.exit_json(changed=False, state="absent")
@@ -178,13 +201,14 @@ def main():
if not module.params['login']:
module.exit_json(failed=True, changed=False, results='Must specifiy a user login.', state="absent")
- content = zapi.get_content(zbx_class_name, 'deletemedia', [content['result'][0][idname]])
+ content = zapi.get_content(zbx_class_name, 'deletemedia', [res[idname] for res in content['result']])
if content.has_key('error'):
module.exit_json(changed=False, results=content['error'], state="absent")
module.exit_json(changed=True, results=content['result'], state="absent")
+ # Create and Update
if state == 'present':
active = get_active(module.params['active'])
mtypeid = get_mediatype(zapi, module.params['mediatype'], module.params['mediatype_desc'])
@@ -197,13 +221,21 @@ def main():
'severity': int(get_severity(module.params['severity'])),
'period': module.params['period'],
}]
+ else:
+ medias = preprocess_medias(zapi, medias)
params = {'users': [zbx_user_query],
'medias': medias,
'output': 'extend',
}
+ ########
+ # Create
+ ########
if not exists(content):
+ if not params['medias']:
+ module.exit_json(changed=False, results=content['result'], state='present')
+
# if we didn't find it, create it
content = zapi.get_content(zbx_class_name, 'addmedia', params)
@@ -216,6 +248,9 @@ def main():
# If user params exists, check to see if they already exist in zabbix
# if they exist, then return as no update
# elif they do not exist, then take user params only
+ ########
+ # Update
+ ########
diff = {'medias': [], 'users': {}}
_ = [diff['medias'].append(media) for media in params['medias'] if not find_media(content['result'], media)]
@@ -225,6 +260,9 @@ def main():
for user in params['users']:
diff['users']['userid'] = user['userid']
+ # Medias have no real unique key so therefore we need to make it like the incoming user's request
+ diff['medias'] = medias
+
# We have differences and need to update
content = zapi.get_content(zbx_class_name, 'updatemedia', diff)
diff --git a/roles/lib_zabbix/tasks/create_template.yml b/roles/lib_zabbix/tasks/create_template.yml
index fd0cdd46f..41381e76c 100644
--- a/roles/lib_zabbix/tasks/create_template.yml
+++ b/roles/lib_zabbix/tasks/create_template.yml
@@ -9,7 +9,8 @@
- set_fact:
- lzbx_applications: "{{ template.zitems | oo_select_keys_from_list(['applications']) | oo_flatten | unique }}"
+ lzbx_item_applications: "{{ template.zitems | default([], True) | oo_select_keys_from_list(['applications']) | oo_flatten | unique }}"
+ lzbx_itemprototype_applications: "{{ template.zitemprototypes | default([], True) | oo_select_keys_from_list(['applications']) | oo_flatten | unique }}"
- name: Create Application
zbx_application:
@@ -18,9 +19,11 @@
zbx_password: "{{ password }}"
name: "{{ item }}"
template_name: "{{ template.name }}"
- with_items: lzbx_applications
+ with_items:
+ - "{{ lzbx_item_applications }}"
+ - "{{ lzbx_itemprototype_applications }}"
register: created_application
- when: template.zitems is defined
+ when: template.zitems is defined or template.zitemprototypes is defined
- name: Create Items
zbx_item:
@@ -52,3 +55,44 @@
url: "{{ item.url | default(None, True) }}"
with_items: template.ztriggers
when: template.ztriggers is defined
+
+- name: Create Discoveryrules
+ zbx_discoveryrule:
+ zbx_server: "{{ server }}"
+ zbx_user: "{{ user }}"
+ zbx_password: "{{ password }}"
+ name: "{{ item.name }}"
+ key: "{{ item.key }}"
+ lifetime: "{{ item.lifetime }}"
+ template_name: "{{ template.name }}"
+ description: "{{ item.description | default('', True) }}"
+ with_items: template.zdiscoveryrules
+ when: template.zdiscoveryrules is defined
+
+- name: Create Item Prototypes
+ zbx_itemprototype:
+ zbx_server: "{{ server }}"
+ zbx_user: "{{ user }}"
+ zbx_password: "{{ password }}"
+ name: "{{ item.name }}"
+ key: "{{ item.key }}"
+ discoveryrule_key: "{{ item.discoveryrule_key }}"
+ value_type: "{{ item.value_type }}"
+ template_name: "{{ template.name }}"
+ applications: "{{ item.applications }}"
+ description: "{{ item.description | default('', True) }}"
+ with_items: template.zitemprototypes
+ when: template.zitemprototypes is defined
+
+- name: Create Trigger Prototypes
+ zbx_triggerprototype:
+ zbx_server: "{{ server }}"
+ zbx_user: "{{ user }}"
+ zbx_password: "{{ password }}"
+ name: "{{ item.name }}"
+ expression: "{{ item.expression }}"
+ url: "{{ item.url | default('', True) }}"
+ priority: "{{ item.priority | default('average', True) }}"
+ description: "{{ item.description | default('', True) }}"
+ with_items: template.ztriggerprototypes
+ when: template.ztriggerprototypes is defined
diff --git a/roles/openshift_examples/defaults/main.yml b/roles/openshift_examples/defaults/main.yml
index 3246790aa..7d4f100e3 100644
--- a/roles/openshift_examples/defaults/main.yml
+++ b/roles/openshift_examples/defaults/main.yml
@@ -14,3 +14,5 @@ db_templates_base: "{{ examples_base }}/db-templates"
xpaas_image_streams: "{{ examples_base }}/xpaas-streams/jboss-image-streams.json"
xpaas_templates_base: "{{ examples_base }}/xpaas-templates"
quickstarts_base: "{{ examples_base }}/quickstart-templates"
+
+openshift_examples_import_command: "create"
diff --git a/roles/openshift_examples/files/examples/xpaas-templates/eap6-https-sti.json b/roles/openshift_examples/files/examples/xpaas-templates/eap6-https-sti.json
index 0497e6824..5df36ccc2 100644
--- a/roles/openshift_examples/files/examples/xpaas-templates/eap6-https-sti.json
+++ b/roles/openshift_examples/files/examples/xpaas-templates/eap6-https-sti.json
@@ -6,10 +6,10 @@
"iconClass" : "icon-jboss",
"description": "Application template for EAP 6 applications built using STI."
},
- "name": "eap6-basic-sti"
+ "name": "eap6-https-sti"
},
"labels": {
- "template": "eap6-basic-sti"
+ "template": "eap6-https-sti"
},
"parameters": [
{
diff --git a/roles/openshift_examples/tasks/main.yml b/roles/openshift_examples/tasks/main.yml
index bfc6dfb0a..3a829a4c6 100644
--- a/roles/openshift_examples/tasks/main.yml
+++ b/roles/openshift_examples/tasks/main.yml
@@ -7,7 +7,7 @@
# RHEL and Centos image streams are mutually exclusive
- name: Import RHEL streams
command: >
- {{ openshift.common.client_binary }} create -n openshift -f {{ rhel_image_streams }}
+ {{ openshift.common.client_binary }} {{ openshift_examples_import_command }} -n openshift -f {{ rhel_image_streams }}
when: openshift_examples_load_rhel
register: oex_import_rhel_streams
failed_when: "'already exists' not in oex_import_rhel_streams.stderr and oex_import_rhel_streams.rc != 0"
@@ -15,7 +15,7 @@
- name: Import Centos Image streams
command: >
- {{ openshift.common.client_binary }} create -n openshift -f {{ centos_image_streams }}
+ {{ openshift.common.client_binary }} {{ openshift_examples_import_command }} -n openshift -f {{ centos_image_streams }}
when: openshift_examples_load_centos | bool
register: oex_import_centos_streams
failed_when: "'already exists' not in oex_import_centos_streams.stderr and oex_import_centos_streams.rc != 0"
@@ -23,7 +23,7 @@
- name: Import db templates
command: >
- {{ openshift.common.client_binary }} create -n openshift -f {{ db_templates_base }}
+ {{ openshift.common.client_binary }} {{ openshift_examples_import_command }} -n openshift -f {{ db_templates_base }}
when: openshift_examples_load_db_templates | bool
register: oex_import_db_templates
failed_when: "'already exists' not in oex_import_db_templates.stderr and oex_import_db_templates.rc != 0"
@@ -31,7 +31,7 @@
- name: Import quickstart-templates
command: >
- {{ openshift.common.client_binary }} create -n openshift -f {{ quickstarts_base }}
+ {{ openshift.common.client_binary }} {{ openshift_examples_import_command }} -n openshift -f {{ quickstarts_base }}
when: openshift_examples_load_quickstarts
register: oex_import_quickstarts
failed_when: "'already exists' not in oex_import_quickstarts.stderr and oex_import_quickstarts.rc != 0"
@@ -40,7 +40,7 @@
- name: Import xPaas image streams
command: >
- {{ openshift.common.client_binary }} create -n openshift -f {{ xpaas_image_streams }}
+ {{ openshift.common.client_binary }} {{ openshift_examples_import_command }} -n openshift -f {{ xpaas_image_streams }}
when: openshift_examples_load_xpaas | bool
register: oex_import_xpaas_streams
failed_when: "'already exists' not in oex_import_xpaas_streams.stderr and oex_import_xpaas_streams.rc != 0"
@@ -48,7 +48,7 @@
- name: Import xPaas templates
command: >
- {{ openshift.common.client_binary }} create -n openshift -f {{ xpaas_templates_base }}
+ {{ openshift.common.client_binary }} {{ openshift_examples_import_command }} -n openshift -f {{ xpaas_templates_base }}
when: openshift_examples_load_xpaas | bool
register: oex_import_xpaas_templates
failed_when: "'already exists' not in oex_import_xpaas_templates.stderr and oex_import_xpaas_templates.rc != 0"
diff --git a/roles/openshift_facts/library/openshift_facts.py b/roles/openshift_facts/library/openshift_facts.py
index 60d1226d4..69bb49c9b 100755
--- a/roles/openshift_facts/library/openshift_facts.py
+++ b/roles/openshift_facts/library/openshift_facts.py
@@ -296,9 +296,8 @@ def set_fluentd_facts_if_unset(facts):
"""
if 'common' in facts:
- deployment_type = facts['common']['deployment_type']
if 'use_fluentd' not in facts['common']:
- use_fluentd = True if deployment_type == 'online' else False
+ use_fluentd = False
facts['common']['use_fluentd'] = use_fluentd
return facts
@@ -461,7 +460,7 @@ def set_deployment_facts_if_unset(facts):
if 'service_type' not in facts['common']:
service_type = 'atomic-openshift'
if deployment_type == 'origin':
- service_type = 'openshift'
+ service_type = 'origin'
elif deployment_type in ['enterprise', 'online']:
service_type = 'openshift'
facts['common']['service_type'] = service_type
@@ -469,26 +468,23 @@ def set_deployment_facts_if_unset(facts):
config_base = '/etc/origin'
if deployment_type in ['enterprise', 'online']:
config_base = '/etc/openshift'
- elif deployment_type == 'origin':
- config_base = '/etc/openshift'
facts['common']['config_base'] = config_base
if 'data_dir' not in facts['common']:
data_dir = '/var/lib/origin'
if deployment_type in ['enterprise', 'online']:
data_dir = '/var/lib/openshift'
- elif deployment_type == 'origin':
- data_dir = '/var/lib/openshift'
facts['common']['data_dir'] = data_dir
+ facts['common']['version'] = get_openshift_version()
for role in ('master', 'node'):
if role in facts:
deployment_type = facts['common']['deployment_type']
if 'registry_url' not in facts[role]:
- registry_url = 'aos3/aos-${component}:${version}'
- if deployment_type in ['enterprise', 'online']:
+ registry_url = 'openshift/origin-${component}:${version}'
+ if deployment_type in ['enterprise', 'online', 'openshift-enterprise']:
registry_url = 'openshift3/ose-${component}:${version}'
- elif deployment_type == 'origin':
- registry_url = 'openshift/origin-${component}:${version}'
+ elif deployment_type == 'atomic-enterprise':
+ registry_url = 'aep3/aep-${component}:${version}'
facts[role]['registry_url'] = registry_url
return facts
@@ -603,6 +599,21 @@ def get_current_config(facts):
return current_config
+def get_openshift_version():
+ """ Get current version of openshift on the host
+
+ Returns:
+ version: the current openshift version
+ """
+ version = ''
+
+ if os.path.isfile('/usr/bin/openshift'):
+ _, output, _ = module.run_command(['/usr/bin/openshift', 'version'])
+ versions = dict(e.split(' v') for e in output.splitlines())
+ version = versions.get('openshift', '')
+
+ #TODO: acknowledge the possility of a containerized install
+ return version
def apply_provider_facts(facts, provider_facts):
""" Apply provider facts to supplied facts dict
@@ -648,7 +659,7 @@ def merge_facts(orig, new):
facts = dict()
for key, value in orig.iteritems():
if key in new:
- if isinstance(value, dict):
+ if isinstance(value, dict) and isinstance(new[key], dict):
facts[key] = merge_facts(value, new[key])
else:
facts[key] = copy.copy(new[key])
diff --git a/roles/openshift_facts/tasks/main.yml b/roles/openshift_facts/tasks/main.yml
index fd3d20800..6301d4fc0 100644
--- a/roles/openshift_facts/tasks/main.yml
+++ b/roles/openshift_facts/tasks/main.yml
@@ -1,5 +1,5 @@
---
-- name: Verify Ansible version is greater than 1.8.0 and not 1.9.0
+- name: Verify Ansible version is greater than 1.8.0 and not 1.9.0 and not 1.9.0.1
assert:
that:
- ansible_version | version_compare('1.8.0', 'ge')
diff --git a/roles/openshift_manage_node/tasks/main.yml b/roles/openshift_manage_node/tasks/main.yml
index 7c4f45ce6..637e494ea 100644
--- a/roles/openshift_manage_node/tasks/main.yml
+++ b/roles/openshift_manage_node/tasks/main.yml
@@ -1,21 +1,21 @@
- name: Wait for Node Registration
command: >
- {{ openshift.common.client_binary }} get node {{ item }}
+ {{ openshift.common.client_binary }} get node {{ item | lower }}
register: omd_get_node
until: omd_get_node.rc == 0
- retries: 10
+ retries: 20
delay: 5
with_items: openshift_nodes
- name: Set node schedulability
command: >
- {{ openshift.common.admin_binary }} manage-node {{ item.openshift.common.hostname }} --schedulable={{ 'true' if item.openshift.node.schedulable | bool else 'false' }}
+ {{ openshift.common.admin_binary }} manage-node {{ item.openshift.common.hostname | lower }} --schedulable={{ 'true' if item.openshift.node.schedulable | bool else 'false' }}
with_items:
- "{{ openshift_node_vars }}"
- name: Label nodes
command: >
- {{ openshift.common.client_binary }} label --overwrite node {{ item.openshift.common.hostname }} {{ item.openshift.node.labels | oo_combine_dict }}
+ {{ openshift.common.client_binary }} label --overwrite node {{ item.openshift.common.hostname | lower }} {{ item.openshift.node.labels | oo_combine_dict }}
with_items:
- "{{ openshift_node_vars }}"
when: "'labels' in item.openshift.node and item.openshift.node.labels != {}"
diff --git a/roles/openshift_master/tasks/main.yml b/roles/openshift_master/tasks/main.yml
index 29b56656f..73c04cb08 100644
--- a/roles/openshift_master/tasks/main.yml
+++ b/roles/openshift_master/tasks/main.yml
@@ -100,6 +100,7 @@
template:
dest: "{{ openshift_master_scheduler_conf }}"
src: scheduler.json.j2
+ backup: true
notify:
- restart master
@@ -129,6 +130,7 @@
template:
dest: "{{ openshift_master_config_file }}"
src: master.yaml.v1.j2
+ backup: true
notify:
- restart master
diff --git a/roles/openshift_master/templates/master.yaml.v1.j2 b/roles/openshift_master/templates/master.yaml.v1.j2
index 500690523..cc1dee13d 100644
--- a/roles/openshift_master/templates/master.yaml.v1.j2
+++ b/roles/openshift_master/templates/master.yaml.v1.j2
@@ -87,7 +87,9 @@ masterPublicURL: {{ openshift.master.public_api_url }}
networkConfig:
clusterNetworkCIDR: {{ openshift.master.sdn_cluster_network_cidr }}
hostSubnetLength: {{ openshift.master.sdn_host_subnet_length }}
+ {% if openshift.common.use_openshift_sdn %}
networkPluginName: {{ openshift.common.sdn_network_plugin_name }}
+ {% endif %}
# serviceNetworkCIDR must match kubernetesMasterConfig.servicesSubnet
serviceNetworkCIDR: {{ openshift.master.portal_net }}
{% include 'v1_partials/oauthConfig.j2' %}
diff --git a/roles/openshift_master/templates/scheduler.json.j2 b/roles/openshift_master/templates/scheduler.json.j2
index 835f2383e..cb5f43bb2 100644
--- a/roles/openshift_master/templates/scheduler.json.j2
+++ b/roles/openshift_master/templates/scheduler.json.j2
@@ -1,4 +1,6 @@
{
+ "kind": "Policy",
+ "apiVersion": "v1",
"predicates": [
{"name": "MatchNodeSelector"},
{"name": "PodFitsResources"},
diff --git a/roles/openshift_master/templates/v1_partials/oauthConfig.j2 b/roles/openshift_master/templates/v1_partials/oauthConfig.j2
index 72889bc29..8a4f5a746 100644
--- a/roles/openshift_master/templates/v1_partials/oauthConfig.j2
+++ b/roles/openshift_master/templates/v1_partials/oauthConfig.j2
@@ -80,6 +80,7 @@ oauthConfig:
provider:
{{ identity_provider_config(identity_provider) }}
{%- endfor %}
+ masterCA: ca.crt
masterPublicURL: {{ openshift.master.public_api_url }}
masterURL: {{ openshift.master.api_url }}
sessionConfig:
diff --git a/roles/openshift_node/tasks/main.yml b/roles/openshift_node/tasks/main.yml
index 1986b631e..d45dd8073 100644
--- a/roles/openshift_node/tasks/main.yml
+++ b/roles/openshift_node/tasks/main.yml
@@ -22,7 +22,7 @@
deployment_type: "{{ openshift_deployment_type }}"
- role: node
local_facts:
- labels: "{{ openshift_node_labels | default(none) }}"
+ labels: "{{ lookup('oo_option', 'openshift_node_labels') | default( openshift_node_labels | default(none), true) }}"
annotations: "{{ openshift_node_annotations | default(none) }}"
registry_url: "{{ oreg_url | default(none) }}"
debug_level: "{{ openshift_node_debug_level | default(openshift.common.debug_level) }}"
@@ -47,6 +47,7 @@
template:
dest: "{{ openshift_node_config_file }}"
src: node.yaml.v1.j2
+ backup: true
notify:
- restart node
diff --git a/roles/openshift_node/templates/node.yaml.v1.j2 b/roles/openshift_node/templates/node.yaml.v1.j2
index 07d80f99b..4931d127e 100644
--- a/roles/openshift_node/templates/node.yaml.v1.j2
+++ b/roles/openshift_node/templates/node.yaml.v1.j2
@@ -12,13 +12,17 @@ kind: NodeConfig
kubeletArguments: {{ openshift.node.kubelet_args | to_json }}
{% endif %}
masterKubeConfig: system:node:{{ openshift.common.hostname }}.kubeconfig
+{% if openshift.common.use_openshift_sdn %}
networkPluginName: {{ openshift.common.sdn_network_plugin_name }}
+{% endif %}
# networkConfig struct introduced in origin 1.0.6 and OSE 3.0.2 which
# deprecates networkPluginName above. The two should match.
networkConfig:
mtu: {{ openshift.node.sdn_mtu }}
+{% if openshift.common.use_openshift_sdn %}
networkPluginName: {{ openshift.common.sdn_network_plugin_name }}
-nodeName: {{ openshift.common.hostname }}
+{% endif %}
+nodeName: {{ openshift.common.hostname | lower }}
podManifestConfig:
servingInfo:
bindAddress: 0.0.0.0:10250
diff --git a/roles/openshift_serviceaccounts/tasks/main.yml b/roles/openshift_serviceaccounts/tasks/main.yml
index 9665d0a72..d93a25a21 100644
--- a/roles/openshift_serviceaccounts/tasks/main.yml
+++ b/roles/openshift_serviceaccounts/tasks/main.yml
@@ -23,4 +23,4 @@
with_items: accounts
- name: Apply new scc rules for service accounts
- command: "{{ openshift.common.client_binary }} replace -f /tmp/scc.yaml"
+ command: "{{ openshift.common.client_binary }} update -f /tmp/scc.yaml"
diff --git a/roles/os_zabbix/tasks/main.yml b/roles/os_zabbix/tasks/main.yml
index f9672b9c4..a503b24d7 100644
--- a/roles/os_zabbix/tasks/main.yml
+++ b/roles/os_zabbix/tasks/main.yml
@@ -11,6 +11,10 @@
- include_vars: template_os_linux.yml
- include_vars: template_docker.yml
- include_vars: template_openshift_master.yml
+- include_vars: template_openshift_node.yml
+- include_vars: template_ops_tools.yml
+- include_vars: template_app_zabbix_server.yml
+- include_vars: template_app_zabbix_agent.yml
- name: Include Template Heartbeat
include: ../../lib_zabbix/tasks/create_template.yml
@@ -43,3 +47,35 @@
server: "{{ ozb_server }}"
user: "{{ ozb_user }}"
password: "{{ ozb_password }}"
+
+- name: Include Template Openshift Node
+ include: ../../lib_zabbix/tasks/create_template.yml
+ vars:
+ template: "{{ g_template_openshift_node }}"
+ server: "{{ ozb_server }}"
+ user: "{{ ozb_user }}"
+ password: "{{ ozb_password }}"
+
+- name: Include Template Ops Tools
+ include: ../../lib_zabbix/tasks/create_template.yml
+ vars:
+ template: "{{ g_template_ops_tools }}"
+ server: "{{ ozb_server }}"
+ user: "{{ ozb_user }}"
+ password: "{{ ozb_password }}"
+
+- name: Include Template App Zabbix Server
+ include: ../../lib_zabbix/tasks/create_template.yml
+ vars:
+ template: "{{ g_template_app_zabbix_server }}"
+ server: "{{ ozb_server }}"
+ user: "{{ ozb_user }}"
+ password: "{{ ozb_password }}"
+
+- name: Include Template App Zabbix Agent
+ include: ../../lib_zabbix/tasks/create_template.yml
+ vars:
+ template: "{{ g_template_app_zabbix_agent }}"
+ server: "{{ ozb_server }}"
+ user: "{{ ozb_user }}"
+ password: "{{ ozb_password }}"
diff --git a/roles/os_zabbix/vars/template_app_zabbix_agent.yml b/roles/os_zabbix/vars/template_app_zabbix_agent.yml
new file mode 100644
index 000000000..06c4eda8b
--- /dev/null
+++ b/roles/os_zabbix/vars/template_app_zabbix_agent.yml
@@ -0,0 +1,23 @@
+---
+g_template_app_zabbix_agent:
+ name: Template App Zabbix Agent
+ zitems:
+ - key: agent.hostname
+ applications:
+ - Zabbix agent
+ value_type: character
+ zabbix_type: '0'
+
+ - key: agent.ping
+ applications:
+ - Zabbix agent
+ description: The agent always returns 1 for this item. It could be used in combination with nodata() for availability check.
+ value_type: int
+ zabbix_type: '0'
+
+ ztriggers:
+ - name: '[Reboot] Zabbix agent on {HOST.NAME} is unreachable for 15 minutes'
+ description: Zabbix agent is unreachable for 15 minutes.
+ expression: '{Template App Zabbix Agent:agent.ping.nodata(15m)}=1'
+ priority: high
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/check_ping.asciidoc
diff --git a/roles/os_zabbix/vars/template_app_zabbix_server.yml b/roles/os_zabbix/vars/template_app_zabbix_server.yml
new file mode 100644
index 000000000..dace2aa29
--- /dev/null
+++ b/roles/os_zabbix/vars/template_app_zabbix_server.yml
@@ -0,0 +1,408 @@
+---
+g_template_app_zabbix_server:
+ name: Template App Zabbix Server
+ zitems:
+ - key: housekeeper_creates
+ applications:
+ - Zabbix server
+ description: A simple count of the number of partition creates output by the housekeeper script.
+ units: ''
+ value_type: int
+ zabbix_type: '2'
+
+ - key: housekeeper_drops
+ applications:
+ - Zabbix server
+ description: A simple count of the number of partition drops output by the housekeeper script.
+ units: ''
+ value_type: int
+ zabbix_type: '2'
+
+ - key: housekeeper_errors
+ applications:
+ - Zabbix server
+ description: A simple count of the number of errors output by the housekeeper script.
+ units: ''
+ value_type: int
+ zabbix_type: '2'
+
+ - key: housekeeper_total
+ applications:
+ - Zabbix server
+ description: A simple count of the total number of lines output by the housekeeper
+ script.
+ units: ''
+ value_type: int
+ zabbix_type: '2'
+
+ - key: zabbix[process,alerter,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,configuration syncer,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,db watchdog,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,discoverer,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,escalator,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,history syncer,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,housekeeper,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,http poller,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,icmp pinger,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,ipmi poller,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,java poller,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,node watcher,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,poller,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,proxy poller,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,self-monitoring,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,snmp trapper,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,timer,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,trapper,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[process,unreachable poller,avg,busy]
+ applications:
+ - Zabbix server
+ description: ''
+ units: '%'
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[queue,10m]
+ applications:
+ - Zabbix server
+ description: ''
+ units: ''
+ value_type: int
+ zabbix_type: '5'
+
+ - key: zabbix[queue]
+ applications:
+ - Zabbix server
+ description: ''
+ units: ''
+ value_type: int
+ zabbix_type: '5'
+
+ - key: zabbix[rcache,buffer,pfree]
+ applications:
+ - Zabbix server
+ description: ''
+ units: ''
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[wcache,history,pfree]
+ applications:
+ - Zabbix server
+ description: ''
+ units: ''
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[wcache,text,pfree]
+ applications:
+ - Zabbix server
+ description: ''
+ units: ''
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[wcache,trend,pfree]
+ applications:
+ - Zabbix server
+ description: ''
+ units: ''
+ value_type: float
+ zabbix_type: '5'
+
+ - key: zabbix[wcache,values]
+ applications:
+ - Zabbix server
+ description: ''
+ units: ''
+ value_type: float
+ zabbix_type: '5'
+ ztriggers:
+ - description: "There has been unexpected output while running the housekeeping script\
+ \ on the Zabbix. There are only three kinds of lines we expect to see in the output,\
+ \ and we've gotten something enw.\r\n\r\nCheck the script's output in /var/lib/zabbix/state\
+ \ for more details."
+ expression: '{Template App Zabbix Server:housekeeper_errors.last(0)}+{Template App Zabbix Server:housekeeper_creates.last(0)}+{Template App Zabbix Server:housekeeper_drops.last(0)}<>{Template App Zabbix Server:housekeeper_total.last(0)}'
+ name: Unexpected output in Zabbix DB Housekeeping
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_DB_Housekeeping.asciidoc
+
+ - description: An error has occurred during running the housekeeping script on the Zabbix. Check the script's output in /var/lib/zabbix/state for more details.
+ expression: '{Template App Zabbix Server:housekeeper_errors.last(0)}>0'
+ name: Errors during Zabbix DB Housekeeping
+ priority: high
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,alerter,avg,busy].min(600)}>75'
+ name: Zabbix alerter processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,configuration syncer,avg,busy].min(600)}>75'
+ name: Zabbix configuration syncer processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,db watchdog,avg,busy].min(600)}>75'
+ name: Zabbix db watchdog processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,discoverer,avg,busy].min(600)}>75'
+ name: Zabbix discoverer processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,escalator,avg,busy].min(600)}>75'
+ name: Zabbix escalator processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,history syncer,avg,busy].min(600)}>75'
+ name: Zabbix history syncer processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,housekeeper,avg,busy].min(1800)}>75'
+ name: Zabbix housekeeper processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,http poller,avg,busy].min(600)}>75'
+ name: Zabbix http poller processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,icmp pinger,avg,busy].min(600)}>75'
+ name: Zabbix icmp pinger processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,ipmi poller,avg,busy].min(600)}>75'
+ name: Zabbix ipmi poller processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,java poller,avg,busy].min(600)}>75'
+ name: Zabbix java poller processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,node watcher,avg,busy].min(600)}>75'
+ name: Zabbix node watcher processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,poller,avg,busy].min(600)}>75'
+ name: Zabbix poller processes more than 75% busy
+ priority: high
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,proxy poller,avg,busy].min(600)}>75'
+ name: Zabbix proxy poller processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,self-monitoring,avg,busy].min(600)}>75'
+ name: Zabbix self-monitoring processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,snmp trapper,avg,busy].min(600)}>75'
+ name: Zabbix snmp trapper processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: Timer processes usually are busy because they have to process time
+ based trigger functions
+ expression: '{Template App Zabbix Server:zabbix[process,timer,avg,busy].min(600)}>75'
+ name: Zabbix timer processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,trapper,avg,busy].min(600)}>75'
+ name: Zabbix trapper processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[process,unreachable poller,avg,busy].min(600)}>75'
+ name: Zabbix unreachable poller processes more than 75% busy
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/Zabbix_state_check.asciidoc
+
+ - description: "This alert generally indicates a performance problem or a problem\
+ \ with the zabbix-server or proxy.\r\n\r\nThe first place to check for issues\
+ \ is Administration > Queue. Be sure to check the general view and the per-proxy\
+ \ view."
+ expression: '{Template App Zabbix Server:zabbix[queue,10m].min(600)}>1000'
+ name: More than 1000 items having missing data for more than 10 minutes
+ priority: high
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/data_lost_overview_plugin.asciidoc
+
+ - description: Consider increasing CacheSize in the zabbix_server.conf configuration
+ file
+ expression: '{Template App Zabbix Server:zabbix[rcache,buffer,pfree].min(600)}<5'
+ name: Less than 5% free in the configuration cache
+ priority: info
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/check_cache.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[wcache,history,pfree].min(600)}<25'
+ name: Less than 25% free in the history cache
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/check_cache.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[wcache,text,pfree].min(600)}<25'
+ name: Less than 25% free in the text history cache
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/check_cache.asciidoc
+
+ - description: ''
+ expression: '{Template App Zabbix Server:zabbix[wcache,trend,pfree].min(600)}<25'
+ name: Less than 25% free in the trends cache
+ priority: avg
+ url: https://github.com/openshift/ops-sop/blob/master/Alerts/check_cache.asciidoc
diff --git a/roles/os_zabbix/vars/template_openshift_master.yml b/roles/os_zabbix/vars/template_openshift_master.yml
index 728423ac1..1de4fefbb 100644
--- a/roles/os_zabbix/vars/template_openshift_master.yml
+++ b/roles/os_zabbix/vars/template_openshift_master.yml
@@ -6,8 +6,53 @@ g_template_openshift_master:
applications:
- Openshift Master
key: create_app
+
+ - key: openshift.master.process.count
+ description: Shows number of master processes running
+ type: int
+ applications:
+ - Openshift Master
+
+ - key: openshift.master.user.count
+ description: Shows number of users in a cluster
+ type: int
+ applications:
+ - Openshift Master
+
+ - key: openshift.master.pod.running.count
+ description: Shows number of pods running
+ type: int
+ applications:
+ - Openshift Master
+
+ - key: openshift.project.counter
+ description: Shows number of projects on a cluster
+ type: int
+ applications:
+ - Openshift Master
+
ztriggers:
- name: 'Application creation has failed on {HOST.NAME}'
expression: '{Template Openshift Master:create_app.last(#1)}=1 and {Template Openshift Master:create_app.last(#2)}=1'
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_create_app.asciidoc'
priority: avg
+
+ - name: 'Openshift Master process not running on {HOST.NAME}'
+ expression: '{Template Openshift Master:openshift.master.process.count.max(#3)}<1'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
+ priority: high
+
+ - name: 'Too many Openshift Master processes running on {HOST.NAME}'
+ expression: '{Template Openshift Master:openshift.master.process.count.min(#3)}>1'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
+ priority: high
+
+ - name: 'Number of users for Openshift Master on {HOST.NAME}'
+ expression: '{Template Openshift Master:openshift.master.user.count.last()}=0'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
+ priority: info
+
+ - name: 'There are no projects running on {HOST.NAME}'
+ expression: '{Template Openshift Master:openshift.project.counter.last()}=0'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
+ priority: info
diff --git a/roles/os_zabbix/vars/template_openshift_node.yml b/roles/os_zabbix/vars/template_openshift_node.yml
new file mode 100644
index 000000000..ce28b1048
--- /dev/null
+++ b/roles/os_zabbix/vars/template_openshift_node.yml
@@ -0,0 +1,44 @@
+---
+g_template_openshift_node:
+ name: Template Openshift Node
+ zitems:
+ - key: openshift.node.process.count
+ description: Shows number of OpenShift Node processes running
+ type: int
+ applications:
+ - Openshift Node
+
+ - key: openshift.node.ovs.pids.count
+ description: Shows number of ovs process ids running
+ type: int
+ applications:
+ - Openshift Node
+
+ - key: openshift.node.ovs.ports.count
+ description: Shows number of OVS ports defined
+ type: int
+ applications:
+ - Openshift Node
+
+ ztriggers:
+ - name: 'Openshift Node process not running on {HOST.NAME}'
+ expression: '{Template Openshift Node:openshift.node.process.count.max(#3)}<1'
+ url: 'https://github.com/openshift/ops-sop/blob/node/V3/Alerts/openshift_node.asciidoc'
+ priority: high
+
+ - name: 'Too many Openshift Node processes running on {HOST.NAME}'
+ expression: '{Template Openshift Node:openshift.node.process.count.min(#3)}>1'
+ url: 'https://github.com/openshift/ops-sop/blob/node/V3/Alerts/openshift_node.asciidoc'
+ priority: high
+
+ - name: 'OVS may not be running on {HOST.NAME}'
+ expression: '{Template Openshift Node:openshift.node.ovs.pids.count.last()}<>4'
+ url: 'https://github.com/openshift/ops-sop/blob/node/V3/Alerts/openshift_node.asciidoc'
+ priority: high
+
+ - name: 'Number of OVS ports is 0 on {HOST.NAME}'
+ expression: '{Template Openshift Node:openshift.node.ovs.ports.count.last()}=0'
+ url: 'https://github.com/openshift/ops-sop/blob/node/V3/Alerts/openshift_node.asciidoc'
+ priority: high
+
+
diff --git a/roles/os_zabbix/vars/template_ops_tools.yml b/roles/os_zabbix/vars/template_ops_tools.yml
new file mode 100644
index 000000000..d1b8a2514
--- /dev/null
+++ b/roles/os_zabbix/vars/template_ops_tools.yml
@@ -0,0 +1,23 @@
+---
+g_template_ops_tools:
+ name: Template Operations Tools
+ zdiscoveryrules:
+ - name: disc.ops.runner
+ key: disc.ops.runner
+ lifetime: 1
+ description: "Dynamically register operations runner items"
+
+ zitemprototypes:
+ - discoveryrule_key: disc.ops.runner
+ name: "Exit code of ops-runner[{#OSO_COMMAND}]"
+ key: "disc.ops.runner.command.exitcode[{#OSO_COMMAND}]"
+ value_type: int
+ description: "The exit code of the command run from ops-runner"
+ applications:
+ - Ops Runner
+
+ ztriggerprototypes:
+ - name: 'ops-runner[{#OSO_COMMAND}]: non-zero exit code on {HOST.NAME}'
+ expression: '{Template Operations Tools:disc.ops.runner.command.exitcode[{#OSO_COMMAND}].last()}<>0'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_ops_runner_command.asciidoc'
+ priority: average
diff --git a/roles/os_zabbix/vars/template_os_linux.yml b/roles/os_zabbix/vars/template_os_linux.yml
index 3173c79b2..69432273f 100644
--- a/roles/os_zabbix/vars/template_os_linux.yml
+++ b/roles/os_zabbix/vars/template_os_linux.yml
@@ -10,17 +10,20 @@ g_template_os_linux:
- key: kernel.all.cpu.wait.total
applications:
- Kernel
- value_type: int
+ value_type: float
+ units: '%'
- key: kernel.all.cpu.irq.hard
applications:
- Kernel
- value_type: int
+ value_type: float
+ units: '%'
- key: kernel.all.cpu.idle
applications:
- Kernel
- value_type: int
+ value_type: float
+ units: '%'
- key: kernel.uname.distro
applications:
@@ -35,7 +38,8 @@ g_template_os_linux:
- key: kernel.all.cpu.irq.soft
applications:
- Kernel
- value_type: int
+ value_type: float
+ units: '%'
- key: kernel.all.load.15_minute
applications:
@@ -45,7 +49,8 @@ g_template_os_linux:
- key: kernel.all.cpu.sys
applications:
- Kernel
- value_type: int
+ value_type: float
+ units: '%'
- key: kernel.all.load.5_minute
applications:
@@ -55,7 +60,8 @@ g_template_os_linux:
- key: kernel.all.cpu.nice
applications:
- Kernel
- value_type: int
+ value_type: float
+ units: '%'
- key: kernel.all.load.1_minute
applications:
@@ -75,7 +81,8 @@ g_template_os_linux:
- key: kernel.all.cpu.user
applications:
- Kernel
- value_type: int
+ value_type: float
+ units: '%'
- key: kernel.uname.machine
applications:
@@ -90,7 +97,8 @@ g_template_os_linux:
- key: kernel.all.cpu.steal
applications:
- Kernel
- value_type: int
+ value_type: float
+ units: '%'
- key: kernel.all.pswitch
applications:
@@ -180,38 +188,51 @@ g_template_os_linux:
multiplier: 1024
units: B
- # Disk items
- - key: filesys.full.xvda2
+ zdiscoveryrules:
+ - name: disc.filesys
+ key: disc.filesys
+ lifetime: 1
+ description: "Dynamically register the filesystems"
+
+ zitemprototypes:
+ - discoveryrule_key: disc.filesys
+ name: "disc.filesys.full.{#OSO_FILESYS}"
+ key: "disc.filesys.full[{#OSO_FILESYS}]"
+ value_type: float
+ description: "PCP filesys.full option. This is the percent full returned from pcp filesys.full"
applications:
- Disk
- value_type: float
- - key: filesys.full.xvda3
+ - discoveryrule_key: disc.filesys
+ name: "Percentage of used inodes on {#OSO_FILESYS}"
+ key: "disc.filesys.inodes.pused[{#OSO_FILESYS}]"
+ value_type: float
+ description: "PCP derived value of percentage of used inodes on a filesystem."
applications:
- Disk
- value_type: float
- ztriggers:
- - name: 'Filesystem: / has less than 10% free on {HOST.NAME}'
- expression: '{Template OS Linux:filesys.full.xvda2.last()}>90'
+ ztriggerprototypes:
+ - name: 'Filesystem: {#OSO_FILESYS} has less than 15% free disk space on {HOST.NAME}'
+ expression: '{Template OS Linux:disc.filesys.full[{#OSO_FILESYS}].last()}>85'
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc'
priority: warn
- - name: 'Filesystem: / has less than 5% free on {HOST.NAME}'
- expression: '{Template OS Linux:filesys.full.xvda2.last()}>95'
+ - name: 'Filesystem: {#OSO_FILESYS} has less than 10% free disk space on {HOST.NAME}'
+ expression: '{Template OS Linux:disc.filesys.full[{#OSO_FILESYS}].last()}>90'
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc'
priority: high
- - name: 'Filesystem: /var has less than 10% free on {HOST.NAME}'
- expression: '{Template OS Linux:filesys.full.xvda3.last()}>90'
+ - name: 'Filesystem: {#OSO_FILESYS} has less than 10% free inodes on {HOST.NAME}'
+ expression: '{Template OS Linux:disc.filesys.inodes.pused[{#OSO_FILESYS}].last()}>90'
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc'
priority: warn
- - name: 'Filesystem: /var has less than 5% free on {HOST.NAME}'
- expression: '{Template OS Linux:filesys.full.xvda3.last()}>95'
+ - name: 'Filesystem: {#OSO_FILESYS} has less than 5% free inodes on {HOST.NAME}'
+ expression: '{Template OS Linux:disc.filesys.inodes.pused[{#OSO_FILESYS}].last()}>95'
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc'
priority: high
+ ztriggers:
- name: 'Too many TOTAL processes on {HOST.NAME}'
expression: '{Template OS Linux:proc.nprocs.last()}>5000'
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_proc.asciidoc'
@@ -222,3 +243,18 @@ g_template_os_linux:
url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_memory.asciidoc'
priority: warn
description: 'Alert on less than 30MegaBytes. This is 30 Million Bytes. 30000 KB x 1024'
+
+ # CPU Utilization #
+ - name: 'CPU idle less than 5% on {HOST.NAME}'
+ expression: '{Template OS Linux:kernel.all.cpu.idle.last()}<5 and {Template OS Linux:kernel.all.cpu.idle.last(#2)}<5'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_cpu_idle.asciidoc'
+ priority: high
+ description: 'CPU is less than 5% idle'
+
+ - name: 'CPU idle less than 10% on {HOST.NAME}'
+ expression: '{Template OS Linux:kernel.all.cpu.idle.last()}<10 and {Template OS Linux:kernel.all.cpu.idle.last(#2)}<10'
+ url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_cpu_idle.asciidoc'
+ priority: warn
+ description: 'CPU is less than 10% idle'
+ dependencies:
+ - 'CPU idle less than 5% on {HOST.NAME}'