diff options
40 files changed, 401 insertions, 140 deletions
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/bin/cluster b/bin/cluster index 486bf2a48..15c99791c 100755 --- a/bin/cluster +++ b/bin/cluster @@ -142,10 +142,14 @@ 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: @@ -164,7 +168,7 @@ class Cluster(object): boto_configs = [conf for conf in boto_conf_files if conf_exists(conf)] if len(key_missing) > 0 and len(boto_configs) == 0: - raise ValueError("PROVIDER aws requires {} environment variable(s). See README_AWS.md".format(missing)) + raise ValueError("PROVIDER aws requires {} environment variable(s). See README_AWS.md".format(key_missing)) elif 'libvirt' == provider: inventory = '-i inventory/libvirt/hosts' @@ -193,7 +197,7 @@ class Cluster(object): if args.option: for opt in args.option: k, v = opt.split('=', 1) - env['cli_' + k] = v + env[k] = v ansible_env = '-e \'{}\''.format( ' '.join(['%s=%s' % (key, value) for (key, value) in env.items()]) diff --git a/inventory/byo/hosts.example b/inventory/byo/hosts.example index 174bff697..df1bae49f 100644 --- a/inventory/byo/hosts.example +++ b/inventory/byo/hosts.example @@ -70,7 +70,7 @@ openshift_master_identity_providers=[{'name': 'htpasswd_auth', 'login': 'true', #osm_default_node_selector='region=primary' # set RPM version for debugging purposes -#openshift_version=-3.0.0.0 +#openshift_pkg_version=-3.0.0.0 # host group for masters [masters] diff --git a/inventory/gce/hosts/gce.py b/inventory/gce/hosts/gce.py index 3403f735e..bf018f1fe 100755 --- a/inventory/gce/hosts/gce.py +++ b/inventory/gce/hosts/gce.py @@ -120,6 +120,8 @@ 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) + print "GCE INI PATH :: "+gce_ini_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 +175,10 @@ class GceInventory(object): args[1] = os.environ.get('GCE_PEM_FILE_PATH', args[1]) kwargs['project'] = os.environ.get('GCE_PROJECT', kwargs['project']) + sys.stderr.write("GCE_EMAIL : "+args[0]+"\n") + sys.stderr.write("GCE_PEM_FILE_PATH : "+args[1]+"\n") + sys.stderr.write("GCE_PROJECT : "+kwargs['project']+"\n") + # Retrieve and return the GCE driver. gce = get_driver(Provider.GCE)(*args, **kwargs) gce.connection.user_agent_append( @@ -211,7 +217,8 @@ 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 +226,8 @@ 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): @@ -284,4 +291,5 @@ class GceInventory(object): # Run the script +print "Hello world" GceInventory() 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/aws/openshift-cluster/vars.online.int.yml b/playbooks/aws/openshift-cluster/vars.online.int.yml index bb18e13b0..2e2f25ccd 100644 --- a/playbooks/aws/openshift-cluster/vars.online.int.yml +++ b/playbooks/aws/openshift-cluster/vars.online.int.yml @@ -3,7 +3,7 @@ ec2_image: ami-9101c8fa ec2_image_name: libra-ops-rhel7* ec2_region: us-east-1 ec2_keypair: mmcgrath_libra -ec2_master_instance_type: t2.small +ec2_master_instance_type: t2.medium ec2_master_security_groups: [ 'integration', 'integration-master' ] ec2_infra_instance_type: c4.large ec2_infra_security_groups: [ 'integration', 'integration-infra' ] diff --git a/playbooks/aws/openshift-cluster/vars.online.prod.yml b/playbooks/aws/openshift-cluster/vars.online.prod.yml index bbef9cc56..18a53e12e 100644 --- a/playbooks/aws/openshift-cluster/vars.online.prod.yml +++ b/playbooks/aws/openshift-cluster/vars.online.prod.yml @@ -3,7 +3,7 @@ ec2_image: ami-9101c8fa ec2_image_name: libra-ops-rhel7* ec2_region: us-east-1 ec2_keypair: mmcgrath_libra -ec2_master_instance_type: t2.small +ec2_master_instance_type: t2.medium ec2_master_security_groups: [ 'production', 'production-master' ] ec2_infra_instance_type: c4.large ec2_infra_security_groups: [ 'production', 'production-infra' ] diff --git a/playbooks/aws/openshift-cluster/vars.online.stage.yml b/playbooks/aws/openshift-cluster/vars.online.stage.yml index 9008a55ba..1f9ac4252 100644 --- a/playbooks/aws/openshift-cluster/vars.online.stage.yml +++ b/playbooks/aws/openshift-cluster/vars.online.stage.yml @@ -3,7 +3,7 @@ ec2_image: ami-9101c8fa ec2_image_name: libra-ops-rhel7* ec2_region: us-east-1 ec2_keypair: mmcgrath_libra -ec2_master_instance_type: t2.small +ec2_master_instance_type: t2.medium ec2_master_security_groups: [ 'stage', 'stage-master' ] ec2_infra_instance_type: c4.large ec2_infra_security_groups: [ 'stage', 'stage-infra' ] diff --git a/playbooks/common/openshift-cluster/set_infra_launch_facts_tasks.yml b/playbooks/common/openshift-cluster/set_infra_launch_facts_tasks.yml new file mode 100644 index 000000000..0fd53eb7d --- /dev/null +++ b/playbooks/common/openshift-cluster/set_infra_launch_facts_tasks.yml @@ -0,0 +1,15 @@ +--- +- set_fact: k8s_type=infra +- set_fact: sub_host_type="{{ type }}" +- set_fact: number_infra="{{ count }}" + +- name: Generate infra instance names(s) + set_fact: + scratch_name: "{{ cluster_id }}-{{ k8s_type }}-{{ sub_host_type }}-{{ '%05x' | format(1048576 | random) }}" + register: infra_names_output + with_sequence: count={{ number_infra }} + +- set_fact: + infra_names: "{{ infra_names_output.results | default([]) + | oo_collect('ansible_facts') + | oo_collect('scratch_name') }}" diff --git a/playbooks/gce/openshift-cluster/config.yml b/playbooks/gce/openshift-cluster/config.yml index fd5dfcc72..7bd3f1a56 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: @@ -22,3 +24,5 @@ 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..613bbb34f --- /dev/null +++ b/playbooks/gce/openshift-cluster/join_node.yml @@ -0,0 +1,64 @@ +--- +- 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: Add to preemptible group if needed + add_host: + name: "{{ node_ip }}" + ansible_ssh_user: "{{ deployment_vars[deployment_type].ssh_user }}" + ansible_sudo: "{{ deployment_vars[deployment_type].sudo }}" + groups: oo_preemptible_nodes + when: preemptible is defined and preemptible == "true" + + - name: Add to not preemptible group if needed + add_host: + name: "{{ node_ip }}" + ansible_ssh_user: "{{ deployment_vars[deployment_type].ssh_user }}" + ansible_sudo: "{{ deployment_vars[deployment_type].sudo }}" + groups: oo_non_preemptible_nodes + when: preemptible is defined and preemptible == "false" + + - 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 + 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..762fa9e8d 100644 --- a/playbooks/gce/openshift-cluster/launch.yml +++ b/playbooks/gce/openshift-cluster/launch.yml @@ -28,7 +28,7 @@ type: "{{ k8s_type }}" g_sub_host_type: "{{ sub_host_type }}" - - include: ../../common/openshift-cluster/set_node_launch_facts_tasks.yml + - include: ../../common/openshift-cluster/set_infra_launch_facts_tasks.yml vars: type: "infra" count: "{{ num_infra }}" diff --git a/playbooks/gce/openshift-cluster/list.yml b/playbooks/gce/openshift-cluster/list.yml index 5ba0f5a48..f5f89baf0 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([]) | difference(['localhost']) | difference(groups.status_terminated | default([])) - 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..f569b2a37 100644 --- a/playbooks/gce/openshift-cluster/tasks/launch_instances.yml +++ b/playbooks/gce/openshift-cluster/tasks/launch_instances.yml @@ -10,18 +10,22 @@ 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 }} register: gce - name: Add new instances to groups and set variables needed add_host: hostname: "{{ item.name }}" - ansible_ssh_host: "{{ item.public_ip }}" + ansible_ssh_host: "{{ item.name }}" ansible_ssh_user: "{{ deployment_vars[deployment_type].ssh_user | default(ansible_ssh_user, true) }}" ansible_sudo: "{{ deployment_vars[deployment_type].sudo }}" groups: "{{ item.tags | oo_prepend_strings_in_list('tag_') | join(',') }}" @@ -30,13 +34,13 @@ with_items: gce.instance_data - name: Wait for ssh - wait_for: port=22 host={{ item.public_ip }} + wait_for: port=22 host={{ item.name }} with_items: gce.instance_data - 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 + retries: 30 + delay: 5 with_items: gce.instance_data diff --git a/playbooks/gce/openshift-cluster/terminate.yml b/playbooks/gce/openshift-cluster/terminate.yml index 098b0df73..f705745d9 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([]) | difference(['localhost']) | difference(groups.status_terminated | default([])) - 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([]) + 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/openstack/openshift-cluster/files/heat_stack.yaml b/playbooks/openstack/openshift-cluster/files/heat_stack.yaml index 40e4ab22c..e3e2b6872 100644 --- a/playbooks/openstack/openshift-cluster/files/heat_stack.yaml +++ b/playbooks/openstack/openshift-cluster/files/heat_stack.yaml @@ -88,6 +88,12 @@ parameters: label: Infra flavor description: Flavor of the infra node servers + key_pair: + type: string + label: Key name + description: Name of the key + + outputs: master_names: @@ -250,6 +256,14 @@ resources: port_range_max: 10250 remote_mode: remote_group_id remote_group_id: { get_resource: master-secgrp } + - direction: ingress + protocol: tcp + port_range_min: 30001 + port_range_max: 30001 + - direction: ingress + protocol: tcp + port_range_min: 30850 + port_range_max: 30850 infra-secgrp: type: OS::Neutron::SecurityGroup @@ -291,7 +305,7 @@ resources: type: master image: { get_param: master_image } flavor: { get_param: master_flavor } - key_name: { get_resource: keypair } + key_name: { get_param: key_pair } net: { get_resource: net } subnet: { get_resource: subnet } secgrp: @@ -323,7 +337,7 @@ resources: subtype: compute image: { get_param: node_image } flavor: { get_param: node_flavor } - key_name: { get_resource: keypair } + key_name: { get_param: key_pair } net: { get_resource: net } subnet: { get_resource: subnet } secgrp: @@ -355,7 +369,7 @@ resources: subtype: infra image: { get_param: infra_image } flavor: { get_param: infra_flavor } - key_name: { get_resource: keypair } + key_name: { get_param: key_pair } net: { get_resource: net } subnet: { get_resource: subnet } secgrp: diff --git a/playbooks/openstack/openshift-cluster/launch.yml b/playbooks/openstack/openshift-cluster/launch.yml index 651aef40b..5f1780476 100644 --- a/playbooks/openstack/openshift-cluster/launch.yml +++ b/playbooks/openstack/openshift-cluster/launch.yml @@ -19,15 +19,32 @@ changed_when: false failed_when: stack_show_result.rc != 0 and 'Stack not found' not in stack_show_result.stderr - - set_fact: - heat_stack_action: 'stack-create' + - name: Create OpenStack Stack + command: 'heat stack-create -f {{ openstack_infra_heat_stack }} + -P key_pair={{ openstack_ssh_keypair }} + -P cluster_id={{ cluster_id }} + -P dns_nameservers={{ openstack_network_dns | join(",") }} + -P cidr={{ openstack_network_cidr }} + -P ssh_incoming={{ openstack_ssh_access_from }} + -P num_masters={{ num_masters }} + -P num_nodes={{ num_nodes }} + -P num_infra={{ num_infra }} + -P master_image={{ deployment_vars[deployment_type].image }} + -P node_image={{ deployment_vars[deployment_type].image }} + -P infra_image={{ deployment_vars[deployment_type].image }} + -P master_flavor={{ openstack_flavor["master"] }} + -P node_flavor={{ openstack_flavor["node"] }} + -P infra_flavor={{ openstack_flavor["infra"] }} + -P ssh_public_key="{{ openstack_ssh_public_key }}" + openshift-ansible-{{ cluster_id }}-stack' when: stack_show_result.rc == 1 - set_fact: heat_stack_action: 'stack-update' when: stack_show_result.rc == 0 - - name: Create or Update OpenStack Stack - command: 'heat {{ heat_stack_action }} -f {{ openstack_infra_heat_stack }} + - name: Update OpenStack Stack + command: 'heat stack-update -f {{ openstack_infra_heat_stack }} + -P key_pair={{ openstack_ssh_keypair }} -P cluster_id={{ cluster_id }} -P cidr={{ openstack_network_cidr }} -P dns_nameservers={{ openstack_network_dns | join(",") }} @@ -50,7 +67,7 @@ shell: 'heat stack-show openshift-ansible-{{ cluster_id }}-stack | awk ''$2 == "stack_status" {print $4}''' register: stack_show_status_result until: stack_show_status_result.stdout not in ['CREATE_IN_PROGRESS', 'UPDATE_IN_PROGRESS'] - retries: 30 + retries: 300 delay: 1 failed_when: stack_show_status_result.stdout not in ['CREATE_COMPLETE', 'UPDATE_COMPLETE'] @@ -119,4 +136,12 @@ - include: update.yml +# Fix icmp reject iptables rules +# It should be solved in openshift-sdn but unfortunately it's not the case +# Mysterious +- name: Configuring Nodes for RBox + hosts: oo_nodes_to_config + roles: + - rbox-node + - include: list.yml diff --git a/roles/lib_zabbix/library/zbx_item.py b/roles/lib_zabbix/library/zbx_item.py index 388db31b9..11e3c7b2b 100644 --- a/roles/lib_zabbix/library/zbx_item.py +++ b/roles/lib_zabbix/library/zbx_item.py @@ -88,6 +88,23 @@ def get_template_id(zapi, template_name): return template_ids, app_ids +def get_multiplier(inval): + ''' Determine the multiplier + ''' + if inval == None or inval == '': + return None, None + + rval = None + try: + rval = int(inval) + except ValueError: + pass + + if rval: + return rval, True + + return rval, False + # The branches are needed for CRUD and error handling # pylint: disable=too-many-branches def main(): @@ -106,6 +123,9 @@ def main(): template_name=dict(default=None, type='str'), zabbix_type=dict(default=2, type='int'), value_type=dict(default='int', type='str'), + multiplier=dict(default=None, type='str'), + description=dict(default=None, type='str'), + units=dict(default=None, type='str'), applications=dict(default=None, type='list'), state=dict(default='present', type='str'), ), @@ -137,11 +157,15 @@ def main(): 'templateids': templateid, }) - # Get + #******# + # GET + #******# if state == 'list': module.exit_json(changed=False, results=content['result'], state="list") - # Delete + #******# + # DELETE + #******# if state == 'absent': if not exists(content): module.exit_json(changed=False, state="absent") @@ -152,12 +176,17 @@ def main(): # Create and Update if state == 'present': + formula, use_multiplier = get_multiplier(module.params['multiplier']) params = {'name': module.params.get('name', module.params['key']), 'key_': module.params['key'], 'hostid': templateid[0], 'type': module.params['zabbix_type'], 'value_type': get_value_type(module.params['value_type']), 'applications': get_app_ids(module.params['applications'], app_name_ids), + 'formula': formula, + 'multiplier': use_multiplier, + 'description': module.params['description'], + 'units': module.params['units'], } # Remove any None valued params diff --git a/roles/lib_zabbix/library/zbx_trigger.py b/roles/lib_zabbix/library/zbx_trigger.py index c384f6fa3..a05de7e68 100644 --- a/roles/lib_zabbix/library/zbx_trigger.py +++ b/roles/lib_zabbix/library/zbx_trigger.py @@ -98,6 +98,7 @@ def main(): zbx_password=dict(default=os.environ.get('ZABBIX_PASSWORD', None), type='str'), zbx_debug=dict(default=False, type='bool'), expression=dict(default=None, type='str'), + name=dict(default=None, type='str'), description=dict(default=None, type='str'), dependencies=dict(default=[], type='list'), priority=dict(default='avg', type='str'), @@ -116,11 +117,11 @@ def main(): zbx_class_name = 'trigger' idname = "triggerid" state = module.params['state'] - description = module.params['description'] + tname = module.params['name'] content = zapi.get_content(zbx_class_name, 'get', - {'filter': {'description': description}, + {'filter': {'description': tname}, 'expandExpression': True, 'selectDependencies': 'triggerid', }) @@ -138,7 +139,8 @@ def main(): # Create and Update if state == 'present': - params = {'description': description, + params = {'description': tname, + 'comments': module.params['description'], 'expression': module.params['expression'], 'dependencies': get_deps(zapi, module.params['dependencies']), 'priority': get_priority(module.params['priority']), diff --git a/roles/lib_zabbix/tasks/create_template.yml b/roles/lib_zabbix/tasks/create_template.yml index bc9aff997..fd0cdd46f 100644 --- a/roles/lib_zabbix/tasks/create_template.yml +++ b/roles/lib_zabbix/tasks/create_template.yml @@ -30,6 +30,9 @@ key: "{{ item.key }}" name: "{{ item.name | default(item.key, true) }}" value_type: "{{ item.value_type | default('int') }}" + description: "{{ item.description | default('', True) }}" + multiplier: "{{ item.multiplier | default('', True) }}" + units: "{{ item.units | default('', True) }}" template_name: "{{ template.name }}" applications: "{{ item.applications }}" with_items: template.zitems @@ -41,8 +44,9 @@ zbx_server: "{{ server }}" zbx_user: "{{ user }}" zbx_password: "{{ password }}" - description: "{{ item.description }}" - dependencies: "{{ item.dependencies | default([], true) }}" + name: "{{ item.name }}" + description: "{{ item.description | default('', True) }}" + dependencies: "{{ item.dependencies | default([], True) }}" expression: "{{ item.expression }}" priority: "{{ item.priority }}" url: "{{ item.url | default(None, True) }}" diff --git a/roles/openshift_common/vars/main.yml b/roles/openshift_common/vars/main.yml index 817fe0a5f..50816d319 100644 --- a/roles/openshift_common/vars/main.yml +++ b/roles/openshift_common/vars/main.yml @@ -5,5 +5,3 @@ # chains with the public zone (or the zone associated with the correct # interfaces) os_firewall_use_firewalld: False - -openshift_data_dir: /var/lib/origin diff --git a/roles/openshift_examples/files/examples/image-streams/image-streams-centos7.json b/roles/openshift_examples/files/examples/image-streams/image-streams-centos7.json index 03affbddf..f213d99ca 100644 --- a/roles/openshift_examples/files/examples/image-streams/image-streams-centos7.json +++ b/roles/openshift_examples/files/examples/image-streams/image-streams-centos7.json @@ -161,19 +161,19 @@ "creationTimestamp": null }, "spec": { - "dockerImageRepository": "openshift/wildfly-8-centos", + "dockerImageRepository": "openshift/wildfly-81-centos7", "tags": [ { "name": "latest" }, { - "name": "8", + "name": "8.1", "annotations": { - "description": "Build and run Java applications on Wildfly 8", + "description": "Build and run Java applications on Wildfly 8.1", "iconClass": "icon-wildfly", "tags": "builder,wildfly,java", - "supports":"wildfly:8,jee,java", - "version": "8" + "supports":"wildfly:8.1,jee,java", + "version": "8.1" }, "from": { "Kind": "ImageStreamTag", @@ -260,13 +260,13 @@ "creationTimestamp": null }, "spec": { - "dockerImageRepository": "openshift/jenkins-16-centos7", + "dockerImageRepository": "openshift/jenkins-1-centos7", "tags": [ { "name": "latest" }, { - "name": "1.6", + "name": "1", "from": { "Kind": "ImageStreamTag", "Name": "latest" diff --git a/roles/openshift_examples/files/examples/image-streams/image-streams-rhel7.json b/roles/openshift_examples/files/examples/image-streams/image-streams-rhel7.json index 0bd885af3..8c125f76a 100644 --- a/roles/openshift_examples/files/examples/image-streams/image-streams-rhel7.json +++ b/roles/openshift_examples/files/examples/image-streams/image-streams-rhel7.json @@ -230,13 +230,13 @@ "creationTimestamp": null }, "spec": { - "dockerImageRepository": "registry.access.redhat.com/openshift3/jenkins-16-rhel7", + "dockerImageRepository": "registry.access.redhat.com/openshift3/jenkins-1-rhel7", "tags": [ { "name": "latest" }, { - "name": "1.6", + "name": "1", "from": { "Kind": "ImageStreamTag", "Name": "latest" diff --git a/roles/openshift_examples/files/examples/quickstart-templates/jenkins-ephemeral-template.json b/roles/openshift_examples/files/examples/quickstart-templates/jenkins-ephemeral-template.json index da08ffbd5..14bd032af 100644 --- a/roles/openshift_examples/files/examples/quickstart-templates/jenkins-ephemeral-template.json +++ b/roles/openshift_examples/files/examples/quickstart-templates/jenkins-ephemeral-template.json @@ -88,7 +88,7 @@ "containers": [ { "name": "jenkins", - "image": "openshift/jenkins-16-centos7", + "image": "${JENKINS_IMAGE}", "env": [ { "name": "JENKINS_PASSWORD", @@ -133,6 +133,11 @@ "value": "jenkins" }, { + "name": "JENKINS_IMAGE", + "description": "Jenkins Docker image to use", + "value": "openshift/jenkins-1-centos7" + }, + { "name": "JENKINS_PASSWORD", "description": "Password for the Jenkins user", "generate": "expression", diff --git a/roles/openshift_examples/files/examples/quickstart-templates/jenkins-persistent-template.json b/roles/openshift_examples/files/examples/quickstart-templates/jenkins-persistent-template.json index 33df68c74..fa31de486 100644 --- a/roles/openshift_examples/files/examples/quickstart-templates/jenkins-persistent-template.json +++ b/roles/openshift_examples/files/examples/quickstart-templates/jenkins-persistent-template.json @@ -105,7 +105,7 @@ "containers": [ { "name": "jenkins", - "image": "openshift/jenkins-16-centos7", + "image": "${JENKINS_IMAGE}", "env": [ { "name": "JENKINS_PASSWORD", @@ -156,6 +156,11 @@ "value": "password" }, { + "name": "JENKINS_IMAGE", + "description": "Jenkins Docker image to use", + "value": "openshift/jenkins-1-centos7" + }, + { "name": "VOLUME_CAPACITY", "description": "Volume space available for data, e.g. 512Mi, 2Gi", "value": "512Mi", diff --git a/roles/openshift_facts/library/openshift_facts.py b/roles/openshift_facts/library/openshift_facts.py index 679c3273a..60d1226d4 100755 --- a/roles/openshift_facts/library/openshift_facts.py +++ b/roles/openshift_facts/library/openshift_facts.py @@ -454,6 +454,8 @@ def set_deployment_facts_if_unset(facts): dict: the facts dict updated with the generated deployment_type facts """ + # Perhaps re-factor this as a map? + # pylint: disable=too-many-branches if 'common' in facts: deployment_type = facts['common']['deployment_type'] if 'service_type' not in facts['common']: @@ -470,6 +472,13 @@ def set_deployment_facts_if_unset(facts): 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 for role in ('master', 'node'): if role in facts: 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..94d7879b2 100644 --- a/roles/openshift_manage_node/tasks/main.yml +++ b/roles/openshift_manage_node/tasks/main.yml @@ -3,7 +3,7 @@ {{ openshift.common.client_binary }} get node {{ item }} register: omd_get_node until: omd_get_node.rc == 0 - retries: 10 + retries: 20 delay: 5 with_items: openshift_nodes diff --git a/roles/openshift_master/tasks/main.yml b/roles/openshift_master/tasks/main.yml index b57711b58..3394d13e5 100644 --- a/roles/openshift_master/tasks/main.yml +++ b/roles/openshift_master/tasks/main.yml @@ -8,6 +8,15 @@ - openshift_master_oauth_grant_method in openshift_master_valid_grant_methods when: openshift_master_oauth_grant_method is defined +- name: Displaying openshift_master_ha + debug: var=openshift_master_ha + +- name: openshift_master_cluster_password + debug: var=openshift_master_cluster_password + +- name: openshift.master.cluster_defer_ha + debug: var=openshift.master.cluster_defer_ha + - fail: msg: "openshift_master_cluster_password must be set for multi-master installations" when: openshift_master_ha | bool and not openshift.master.cluster_defer_ha | bool and openshift_master_cluster_password is not defined @@ -23,7 +32,7 @@ api_port: "{{ openshift_master_api_port | default(None) }}" api_url: "{{ openshift_master_api_url | default(None) }}" api_use_ssl: "{{ openshift_master_api_use_ssl | default(None) }}" - public_api_url: "{{ openshift_master_public_api_url | default(None) }}" + public_api_url: "{{ openshift_master_public_api_url | default('https://' ~ openshift.common.public_ip ~ ':8443') }}" console_path: "{{ openshift_master_console_path | default(None) }}" console_port: "{{ openshift_master_console_port | default(None) }}" console_url: "{{ openshift_master_console_url | default(None) }}" diff --git a/roles/openshift_master/templates/master.yaml.v1.j2 b/roles/openshift_master/templates/master.yaml.v1.j2 index 7aa4ce9b6..500690523 100644 --- a/roles/openshift_master/templates/master.yaml.v1.j2 +++ b/roles/openshift_master/templates/master.yaml.v1.j2 @@ -46,7 +46,7 @@ etcdConfig: certFile: etcd.server.crt clientCA: ca.crt keyFile: etcd.server.key - storageDirectory: {{ openshift_data_dir }}/openshift.local.etcd + storageDirectory: {{ openshift.common.data_dir }}/openshift.local.etcd {% endif %} etcdStorageConfig: kubernetesStoragePrefix: kubernetes.io diff --git a/roles/openshift_master/vars/main.yml b/roles/openshift_master/vars/main.yml index cce118cf1..ecdb4f883 100644 --- a/roles/openshift_master/vars/main.yml +++ b/roles/openshift_master/vars/main.yml @@ -3,7 +3,7 @@ openshift_master_config_dir: "{{ openshift.common.config_base }}/master" openshift_master_config_file: "{{ openshift_master_config_dir }}/master-config.yaml" openshift_master_scheduler_conf: "{{ openshift_master_config_dir }}/scheduler.json" openshift_master_policy: "{{ openshift_master_config_dir }}/policy.json" -openshift_version: "{{ openshift_version | default('') }}" +openshift_version: "{{ openshift_pkg_version | default('') }}" openshift_master_valid_grant_methods: - auto diff --git a/roles/openshift_master_ca/vars/main.yml b/roles/openshift_master_ca/vars/main.yml index 9e9561e02..b35339b18 100644 --- a/roles/openshift_master_ca/vars/main.yml +++ b/roles/openshift_master_ca/vars/main.yml @@ -3,4 +3,4 @@ openshift_master_config_dir: "{{ openshift.common.config_base }}/master" openshift_master_ca_cert: "{{ openshift_master_config_dir }}/ca.crt" openshift_master_ca_key: "{{ openshift_master_config_dir }}/ca.key" openshift_master_ca_serial: "{{ openshift_master_config_dir }}/ca.serial.txt" -openshift_version: "{{ openshift_version | default('') }}" +openshift_version: "{{ openshift_pkg_version | default('') }}" diff --git a/roles/openshift_node/tasks/main.yml b/roles/openshift_node/tasks/main.yml index 1986b631e..b32c3a4b3 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() ) }}" annotations: "{{ openshift_node_annotations | default(none) }}" registry_url: "{{ oreg_url | default(none) }}" debug_level: "{{ openshift_node_debug_level | default(openshift.common.debug_level) }}" @@ -72,6 +72,12 @@ dest: /etc/sysconfig/docker regexp: '^OPTIONS=.*$' line: "OPTIONS='--insecure-registry={{ openshift.node.portal_net }} \ +--insecure-registry=dockerhub.rnd.amadeus.net:5000 \ +--insecure-registry=dockerhub.rnd.amadeus.net:5001 \ +--insecure-registry=dockerhub.rnd.amadeus.net:5002 \ +--add-registry=dockerhub.rnd.amadeus.net:5000 \ +--add-registry=dockerhub.rnd.amadeus.net:5001 \ +--add-registry=dockerhub.rnd.amadeus.net:5002 \ {% if ansible_selinux and ansible_selinux.status == '''enabled''' %}--selinux-enabled{% endif %}'" when: docker_check.stat.isreg notify: diff --git a/roles/openshift_node/templates/node.yaml.v1.j2 b/roles/openshift_node/templates/node.yaml.v1.j2 index 0f708fb55..07d80f99b 100644 --- a/roles/openshift_node/templates/node.yaml.v1.j2 +++ b/roles/openshift_node/templates/node.yaml.v1.j2 @@ -25,5 +25,5 @@ servingInfo: certFile: server.crt clientCA: ca.crt keyFile: server.key -volumeDirectory: {{ openshift_data_dir }}/openshift.local.volumes +volumeDirectory: {{ openshift.common.data_dir }}/openshift.local.volumes {% include 'partials/kubeletArguments.j2' %} diff --git a/roles/openshift_node/vars/main.yml b/roles/openshift_node/vars/main.yml index db2c3e15a..43dc50ca8 100644 --- a/roles/openshift_node/vars/main.yml +++ b/roles/openshift_node/vars/main.yml @@ -1,4 +1,4 @@ --- openshift_node_config_dir: "{{ openshift.common.config_base }}/node" openshift_node_config_file: "{{ openshift_node_config_dir }}/node-config.yaml" -openshift_version: "{{ openshift_version | default('') }}" +openshift_version: "{{ openshift_pkg_version | default('') }}" diff --git a/roles/os_zabbix/vars/template_docker.yml b/roles/os_zabbix/vars/template_docker.yml index a1cd3519e..395e054de 100644 --- a/roles/os_zabbix/vars/template_docker.yml +++ b/roles/os_zabbix/vars/template_docker.yml @@ -52,35 +52,35 @@ g_template_docker: - Docker Storage value_type: float ztriggers: - - description: 'docker.ping failed on {HOST.NAME}' + - name: 'docker.ping failed on {HOST.NAME}' expression: '{Template Docker:docker.ping.max(#3)}<1' url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_docker_ping.asciidoc' priority: high - - description: 'Docker storage is using LOOPBACK on {HOST.NAME}' + - name: 'Docker storage is using LOOPBACK on {HOST.NAME}' expression: '{Template Docker:docker.storage.is_loopback.last()}<>0' url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_docker_loopback.asciidoc' priority: high - - description: 'Critically low docker storage data space on {HOST.NAME}' + - name: 'Critically low docker storage data space on {HOST.NAME}' expression: '{Template Docker:docker.storage.data.space.percent_available.max(#3)}<5 or {Template Docker:docker.storage.data.space.available.max(#3)}<5' # < 5% or < 5GB url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_docker_storage.asciidoc' priority: high - - description: 'Critically low docker storage metadata space on {HOST.NAME}' + - name: 'Critically low docker storage metadata space on {HOST.NAME}' expression: '{Template Docker:docker.storage.metadata.space.percent_available.max(#3)}<5 or {Template Docker:docker.storage.metadata.space.available.max(#3)}<0.005' # < 5% or < 5MB url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_docker_storage.asciidoc' priority: high # Put triggers that depend on other triggers here (deps must be created first) - - description: 'Low docker storage data space on {HOST.NAME}' + - name: 'Low docker storage data space on {HOST.NAME}' expression: '{Template Docker:docker.storage.data.space.percent_available.max(#3)}<10 or {Template Docker:docker.storage.data.space.available.max(#3)}<10' # < 10% or < 10GB url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_docker_storage.asciidoc' dependencies: - 'Critically low docker storage data space on {HOST.NAME}' priority: average - - description: 'Low docker storage metadata space on {HOST.NAME}' + - name: 'Low docker storage metadata space on {HOST.NAME}' expression: '{Template Docker:docker.storage.metadata.space.percent_available.max(#3)}<10 or {Template Docker:docker.storage.metadata.space.available.max(#3)}<0.01' # < 10% or < 10MB url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_docker_storage.asciidoc' dependencies: diff --git a/roles/os_zabbix/vars/template_heartbeat.yml b/roles/os_zabbix/vars/template_heartbeat.yml index 798377cd9..8dbe0d0d6 100644 --- a/roles/os_zabbix/vars/template_heartbeat.yml +++ b/roles/os_zabbix/vars/template_heartbeat.yml @@ -7,7 +7,7 @@ g_template_heartbeat: - Heartbeat key: heartbeat.ping ztriggers: - - description: 'Heartbeat.ping has failed on {HOST.NAME}' + - name: 'Heartbeat.ping has failed on {HOST.NAME}' expression: '{Template Heartbeat:heartbeat.ping.nodata(20m)}=1' priority: avg url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_node_heartbeat.asciidoc' diff --git a/roles/os_zabbix/vars/template_openshift_master.yml b/roles/os_zabbix/vars/template_openshift_master.yml index d2c1365b0..728423ac1 100644 --- a/roles/os_zabbix/vars/template_openshift_master.yml +++ b/roles/os_zabbix/vars/template_openshift_master.yml @@ -7,7 +7,7 @@ g_template_openshift_master: - Openshift Master key: create_app ztriggers: - - description: 'Application creation has failed on {HOST.NAME}' + - 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 diff --git a/roles/os_zabbix/vars/template_os_linux.yml b/roles/os_zabbix/vars/template_os_linux.yml index 7c446cd85..3173c79b2 100644 --- a/roles/os_zabbix/vars/template_os_linux.yml +++ b/roles/os_zabbix/vars/template_os_linux.yml @@ -52,106 +52,135 @@ g_template_os_linux: - Kernel value_type: float - - key: mem.freemem + - key: kernel.all.cpu.nice applications: - - Memory + - Kernel value_type: int - - key: kernel.all.cpu.nice + - key: kernel.all.load.1_minute applications: - Kernel - value_type: int + value_type: float - - key: mem.util.bufmem + - key: kernel.uname.version applications: - - Memory - value_type: int + - Kernel + value_type: string - - key: swap.used + - key: kernel.all.uptime applications: - - Memory + - Kernel value_type: int - - key: kernel.all.load.1_minute + - key: kernel.all.cpu.user applications: - Kernel - value_type: float + value_type: int - - key: kernel.uname.version + - key: kernel.uname.machine applications: - Kernel value_type: string - - key: swap.length + - key: hinv.ncpu applications: - - Memory + - Kernel value_type: int - - key: mem.physmem + - key: kernel.all.cpu.steal applications: - - Memory + - Kernel value_type: int - - key: kernel.all.uptime + - key: kernel.all.pswitch applications: - Kernel value_type: int - - key: swap.free + - key: kernel.uname.release applications: - - Memory - value_type: int + - Kernel + value_type: string - - key: mem.util.available + - key: proc.nprocs applications: - - Memory + - Kernel value_type: int - - key: mem.util.used + # Memory Items + - key: mem.freemem applications: - Memory value_type: int + description: "PCP: free system memory metric from /proc/meminfo" + multiplier: 1024 + units: B - - key: kernel.all.cpu.user + - key: mem.util.bufmem applications: - - Kernel + - Memory value_type: int + description: "PCP: Memory allocated for buffer_heads.; I/O buffers metric from /proc/meminfo" + multiplier: 1024 + units: B - - key: kernel.uname.machine + - key: swap.used applications: - - Kernel - value_type: string + - Memory + value_type: int + description: "PCP: swap used metric from /proc/meminfo" + multiplier: 1024 + units: B - - key: hinv.ncpu + - key: swap.length applications: - - Kernel + - Memory value_type: int + description: "PCP: total swap available metric from /proc/meminfo" + multiplier: 1024 + units: B - - key: mem.util.cached + - key: mem.physmem applications: - Memory value_type: int + description: "PCP: The value of this metric corresponds to the \"MemTotal\" field reported by /proc/meminfo. Note that this does not necessarily correspond to actual installed physical memory - there may be areas of the physical address space mapped as ROM in various peripheral devices and the bios may be mirroring certain ROMs in RAM." + multiplier: 1024 + units: B - - key: kernel.all.cpu.steal + - key: swap.free applications: - - Kernel + - Memory value_type: int + description: "PCP: swap free metric from /proc/meminfo" + multiplier: 1024 + units: B - - key: kernel.all.pswitch + - key: mem.util.available applications: - - Kernel + - Memory value_type: int + description: "PCP: The amount of memory that is available for a new workload, without pushing the system into swap. Estimated from MemFree, Active(file), Inactive(file), and SReclaimable, as well as the \"low\" watermarks from /proc/zoneinfo.; available memory from /proc/meminfo" + multiplier: 1024 + units: B - - key: kernel.uname.release + - key: mem.util.used applications: - - Kernel - value_type: string + - Memory + value_type: int + description: "PCP: Used memory is the difference between mem.physmem and mem.freemem; used memory metric from /proc/meminfo" + multiplier: 1024 + units: B - - key: proc.nprocs + - key: mem.util.cached applications: - - Kernel + - Memory value_type: int + description: "PCP: Memory used by the page cache, including buffered file data. This is in-memory cache for files read from the disk (the pagecache) but doesn't include SwapCached.; page cache metric from /proc/meminfo" + multiplier: 1024 + units: B + # Disk items - key: filesys.full.xvda2 applications: - Disk @@ -163,32 +192,33 @@ g_template_os_linux: value_type: float ztriggers: - - description: 'Filesystem: / has less than 10% free on {HOST.NAME}' + - name: 'Filesystem: / has less than 10% free on {HOST.NAME}' expression: '{Template OS Linux:filesys.full.xvda2.last()}>90' url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc' priority: warn - - description: 'Filesystem: / has less than 5% free on {HOST.NAME}' + - name: 'Filesystem: / has less than 5% free on {HOST.NAME}' expression: '{Template OS Linux:filesys.full.xvda2.last()}>95' url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc' priority: high - - description: 'Filesystem: /var has less than 10% free on {HOST.NAME}' + - name: 'Filesystem: /var has less than 10% free on {HOST.NAME}' expression: '{Template OS Linux:filesys.full.xvda3.last()}>90' url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc' priority: warn - - description: 'Filesystem: /var has less than 5% free on {HOST.NAME}' + - name: 'Filesystem: /var has less than 5% free on {HOST.NAME}' expression: '{Template OS Linux:filesys.full.xvda3.last()}>95' url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_filesys_full.asciidoc' priority: high - - description: 'Too many TOTAL processes on {HOST.NAME}' + - 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' priority: warn - - description: 'Lack of available memory on {HOST.NAME}' - expression: '{Template OS Linux:mem.freemem.last()}<3000' + - name: 'Lack of available memory on {HOST.NAME}' + expression: '{Template OS Linux:mem.freemem.last()}<30720000' 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' |