From d0b167bd075eda5ffa104229103dfad772e9f403 Mon Sep 17 00:00:00 2001 From: Chengcheng Mu Date: Tue, 18 Aug 2015 10:46:23 +0200 Subject: fixed some issues to boot VM on GCE corrected openshift master config, commented infra correct list and terminate, it was bugged in case where no instance were terminated Using openshift-sdn for gce new join_node playbook for gce openstack/hosts/nova.py is now taking the nova/ini of its directory and not the directory of execution of bin/cluster add fix of ICMP reject rules Avoid a recursive loop Jenkins image was renamed Default masters to t2.medium instead of t2.small Fix a minor bug involving AWS ENV Keys * If a user forgot to set their AWS keys, we'd get a non descriptive error about a variable not being set * This patch uses the correct variable so the error message is more informative delete some fix that are needed anymore (selinux, iptables rules for sdn) GCE : all variables needed are in gce.ini, it will be used by bin/cluster (now check better the presence of gce.init in the default place or use GCE_INI_PATH to locate it ), also by gce.ini openshift_node_labels : get from oo_option fix syntax error in bin/cluster fix lookup for openshift_node_labels Adding desc, multiplier, and units to zabbix item Adding capability to have descriptions on triggers updated triggers and items to have better descriptions and multipliers Move openshift_data_dir to a fact based on deployment_type Previously this was being set to /var/lib/origin regardless of deployment_type which isn't correct given that existing 'enterprise' and 'online' deployments would have been deployed with /var/lib/openshift Verify again that ansible version is different than 1.9.0 and 1.9.0.1 bin/cluste does not take -a and -s anymore fix master_public_api_url : using by default a correct url Really fixed master public api url this time Really fixed master public api url this time uncommented infra deployment like before fixed again masterpublicurl in a template README_GCE.md : use GCE_INI_PATH in order to locate gce.ini, update description of gce.ini --- .../aws/openshift-cluster/vars.online.int.yml | 2 +- .../aws/openshift-cluster/vars.online.prod.yml | 2 +- .../aws/openshift-cluster/vars.online.stage.yml | 2 +- .../set_infra_launch_facts_tasks.yml | 15 +++++ playbooks/gce/openshift-cluster/config.yml | 4 ++ playbooks/gce/openshift-cluster/join_node.yml | 64 ++++++++++++++++++++++ playbooks/gce/openshift-cluster/launch.yml | 2 +- playbooks/gce/openshift-cluster/list.yml | 4 +- .../openshift-cluster/tasks/launch_instances.yml | 14 +++-- playbooks/gce/openshift-cluster/terminate.yml | 55 ++++++++++++------- playbooks/gce/openshift-cluster/vars.yml | 8 ++- .../openshift-cluster/files/heat_stack.yaml | 20 ++++++- playbooks/openstack/openshift-cluster/launch.yml | 35 ++++++++++-- 13 files changed, 184 insertions(+), 43 deletions(-) create mode 100644 playbooks/common/openshift-cluster/set_infra_launch_facts_tasks.yml create mode 100644 playbooks/gce/openshift-cluster/join_node.yml (limited to 'playbooks') 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 -- cgit v1.2.3