[patch] multiple quick winner fixes (#966)

docs/playbooks/oneclick-visualinspection.md

@@ -21,6 +21,10 @@ All timings are estimates, see the individual pages for each of these playbooks
 - `MAS_CONFIG_DIR` Directory where generated config files will be saved (you may also provide pre-generated config files here)
 - `IBM_ENTITLEMENT_KEY` Your IBM Entitlement key to access the IBM Container Registry
 
+## Optional environment variables
+- `MAS_APP_SETTINGS_VISUALINSPECTION_STORAGE_CLASS` Defines a custom file storage class for Visual Inspection application. If none provided, then a default storage class will be auto defined accordingly to your cluster's availability i.e `ibmc-file-gold` for IBM Cloud or `azurefiles-premium` for Azure clusters.
+- `MAS_APP_SETTINGS_VISUALINSPECTION_STORAGE_SIZE` Defines persistent storage size for Visual Inspection application. If not provided, default is `100Gi`.
+
 ## Usage
 ```bash
 export MAS_INSTANCE_ID=inst1

ibm/mas_devops/roles/configure_manage_eventstreams/defaults/main.yml

@@ -22,5 +22,5 @@ mas_app_ws_fqn: "{{ lookup('env','MAS_APP_WS_FQN') | default('manageworkspaces.a
 mas_app_ws_apiversion: apps.mas.ibm.com/v1
 mas_app_ws_kind: ManageWorkspace
 
-mas_app_cfg_timeout: 480  # 8 minutes before we give up and fall back into the retry loop
-mas_app_cfg_retries: 50   # 8 mins each loop * 50 loops =~ 400 minutes / 6 2/3 hours (Manage is really slow to set up)
+mas_app_cfg_timeout: "{{ lookup('env', 'MAS_APP_CFG_TIMEOUT') | default(480, true)}}" # 8 minutes before we give up and fall back into the retry loop
+mas_app_cfg_retries: "{{ lookup('env', 'MAS_APP_CFG_RETRIES') | default(50, true)}}"  # 8 mins each loop * 50 loops =~ 400 minutes / 6 2/3 hours (Manage is really slow to set up)

ibm/mas_devops/roles/cp4d_service/tasks/wait/wait-wd.yml

@@ -119,6 +119,17 @@
     - cpd_cr_wait_lookup.resources[0].status.watsonDiscoveryStatus != "Completed"
   include_tasks: wait-wd-detectimagepullbackoff.yml
 
+# Adding this in an attempt to have WD installs completing successfully in a consistent way
+# in few occasions wd-discovery-ranker-rest pod fails to start up due some other WD pods not running properly
+# thus this forces all wd pods to be rebooted with the hopes that it does the trick to have them all up and running
+- name: "wait-wd : Restart all wd pods to prevent intermitent failures with wd-discovery-ranker-rest"
+  when:
+    - cpd_cr_wait_lookup.resources is defined
+    - cpd_cr_wait_lookup.resources | length == 1
+    - cpd_cr_wait_lookup.resources[0].status is defined
+    - cpd_cr_wait_lookup.resources[0].status.watsonDiscoveryStatus is defined
+    - cpd_cr_wait_lookup.resources[0].status.watsonDiscoveryStatus != "Completed"
+  shell: "oc get pods -n {{ cpd_instance_namespace }} | awk '{print $1}'| grep wd- | xargs oc delete pod -n {{ cpd_instance_namespace }}"
 
 # 4. Wait for CP4D service CR to be ready
 # -----------------------------------------------------------------------------

ibm/mas_devops/roles/gencfg_workspace/tasks/main.yml

@@ -1,5 +1,4 @@
 ---
-
 # 1. Check for undefined properties that do not have a default
 # -----------------------------------------------------------------------------
 - name: "Assert that mas_instance_id has been provided"
@@ -17,11 +16,19 @@
     that: mas_workspace_name is defined and mas_workspace_name != ""
     fail_msg: "mas_workspace_name property has not been set"
 
+- name: "Fail if mas_workspace_id does not meet requirements"
+  assert:
+    that: mas_workspace_id is match ('^[a-z][a-z0-9]{2,11}$')
+    fail_msg:
+      - "mas_workspace_id does not meet requirements"
+      - "Must be 3-12 characters long"
+      - "Must only use lowercase letters and numbers"
+      - "Must start with a lowercase letter"
 
 # 2. Generate Workspace for MAS
 # -----------------------------------------------------------------------------
 - name: Copy Workspace to filesytem
   ansible.builtin.template:
     src: workspace.yml.j2
     dest: "{{ mas_config_dir }}/workspace-{{ mas_workspace_id }}.yml"
-    mode: '664'
+    mode: "664"

ibm/mas_devops/roles/install_operator/tasks/main.yml

@@ -1,33 +1,30 @@
 ---
-
 # 1. Create namespace we will deploy to
 # -----------------------------------------------------------------------------
 - name: "Create namespace"
   kubernetes.core.k8s:
     api_version: v1
     kind: Namespace
-    name: '{{ namespace }}'
-
+    name: "{{ namespace }}"
 
 - name: Add custom labels to namespace
   when: custom_labels is defined and custom_labels | length > 0
   kubernetes.core.k8s:
     state: patched
     kind: Namespace
-    name: '{{ namespace }}'
+    name: "{{ namespace }}"
     definition: "{{ lookup('template', 'templates/custom_labels.json.j2') }}"
 
-
 # 2. Create an image pull secret for the pre-release catalog
 # -----------------------------------------------------------------------------
 - name: "Debug Entitlement Secret Creation"
   debug:
     msg:
       - "Target Namespace ....................... {{ namespace }}"
       - "Artifactory Username ................... {{ artifactory_username | default('<undefined>', true) }}"
-      - "Artifactory Password ................... {{ artifactory_token | default('<undefined>', true) }}"
+      - "Artifactory Password ................... {{ '************' if (artifactory_token is defined) else '<undefined>' }}"
       - "ICR Username ........................... {{ icr_username | default('<undefined>', true) }}"
-      - "ICR Password ........................... {{ icr_password | default('<undefined>', true) }}"
+      - "ICR Password ........................... {{ '************' if (icr_password is defined) else '<undefined>' }}"
 
 - name: "Create ibm-entitlement secret"
   kubernetes.core.k8s:
@@ -37,11 +34,10 @@
       type: kubernetes.io/dockerconfigjson
       metadata:
         name: ibm-entitlement
-        namespace: '{{ namespace }}'
+        namespace: "{{ namespace }}"
       data:
         .dockerconfigjson: "{{ lookup('template', 'templates/ibm-entitlement-with-artifactory.json.j2') | to_json | b64encode }}"
 
-
 # 3. Patch the default service account for pre-release build access
 # -----------------------------------------------------------------------------
 # If we don't do this then we won't be able to pull the operator image from
@@ -56,11 +52,10 @@
       kind: ServiceAccount
       metadata:
         name: default
-        namespace: '{{ namespace }}'
+        namespace: "{{ namespace }}"
       imagePullSecrets:
         - name: ibm-entitlement
 
-
 # 4. Create the operator group that will scope the operator
 # -----------------------------------------------------------------------------
 - name: "Create operator group"
@@ -69,7 +64,6 @@
     wait: yes
     wait_timeout: 60 # subsequent tasks will fail if the group isn't fully created
 
-
 # 5. Create the subscription for the operator
 # -----------------------------------------------------------------------------
 - name: "Create subscription"
@@ -78,5 +72,5 @@
     wait: yes
     wait_timeout: 300
     wait_condition:
-      type: 'CatalogSourcesUnhealthy'
+      type: "CatalogSourcesUnhealthy"
       status: "False"

ibm/mas_devops/roles/kafka/README.md

@@ -1,14 +1,15 @@
 kafka
 =====
 
-This role provides support to install a Kafka Cluster using [Red Hat AMQ Streams](https://www.redhat.com/en/resources/amq-streams-datasheet), IBM Event Streams or AWS MSK and generate configuration that can be directly applied to Maximo Application Suite.
+This role provides support to install a Kafka Cluster using [Red Hat AMQ Streams](https://www.redhat.com/en/resources/amq-streams-datasheet), [IBM Event Streams](https://www.ibm.com/cloud/event-streams) or [AWS MSK](https://aws.amazon.com/msk/) and generate configuration that can be directly applied to Maximo Application Suite.
 
 > The Red Hat AMQ streams component is a massively scalable, distributed, and high-performance data streaming platform based on the Apache Kafka project. It offers a distributed backbone that allows microservices and other applications to share data with high throughput and low latency.
 >
 > As more applications move to Kubernetes and Red Hat OpenShift, it is increasingly important to be able to run the communication infrastructure on the same platform. Red Hat OpenShift, as a highly scalable platform, is a natural fit for messaging technologies such as Kafka. The AMQ streams component makes running and managing Apache Kafka OpenShift native through the use of powerful operators that simplify the deployment, configuration, management, and use of Apache Kafka on Red Hat OpenShift.
 >
 > The AMQ streams component is part of the Red Hat AMQ family, which also includes the AMQ broker, a longtime innovation leader in Java™ Message Service (JMS) and polyglot messaging, as well as the AMQ interconnect router, a wide-area, peer-to-peer messaging solution.
 
+**Note:** The MAS license does not include entitlement for AMQ streams. The MAS Devops Collection supports this Kafka deployment as an example only.
 
 !!! tip
     The role will generate a yaml file containing the definition of a Secret and KafkaCfg resource that can be used to configure the deployed cluster as the MAS system Kafka.

ibm/mas_devops/roles/mongodb/tasks/providers/community/install.yml

@@ -304,13 +304,6 @@
         namespace: "{{ mongodb_namespace }}"
       register: mongodb_crt_lookup
 
-    - name: "community : install : Create MAS MongoCfg (debug)"
-      debug:
-        msg: "{{ lookup('template', 'templates/community/suite_mongocfg.yml.j2') }}"
-      vars:
-        mongodb_ca_pem: "{{ mongodb_ca_lookup.resources[0].data['ca.crt'] }}"
-        mongodb_admin_password: "{{ admin_password_lookup.resources[0].data.password | b64decode }}"
-
     - name: "community : install : Create MAS MongoCfg"
       when:
         - mas_instance_id is defined

ibm/mas_devops/roles/ocp_config/defaults/main.yml

@@ -13,4 +13,4 @@ ocp_ingress_server_timeout: "{{ lookup('env', 'OCP_INGRESS_SERVER_TIMEOUT') | de
 
 # Ingress Controller Settings
 # -----------------------------------------------------------------------------
-ocp_operatorhub_disable_redhat_sources: "{{ lookup('env', 'OCP_OPERATORHUB_DISABLE_REDHAT_SOURCES') | default('30s', true) }}"
+ocp_operatorhub_disable_redhat_sources: "{{ lookup('env', 'OCP_OPERATORHUB_DISABLE_REDHAT_SOURCES') | default('False', true) | bool }}"

ibm/mas_devops/roles/ocp_provision/defaults/main.yml

@@ -14,7 +14,6 @@ supported_cluster_types:
   - rosa
   - ipi
 
-
 # GPU support (limited)
 # -----------------------------------------------------------------------------
 # Flag to add GPU worker node to cluster. Currently only set up for ROKS clusters
@@ -26,7 +25,6 @@ gpu_workers: "{{ lookup('env', 'GPU_WORKERS') | default('1', true) }}"
 # The name of the gpu worker pool.
 gpu_workerpool_name: "{{ lookup('env', 'GPU_WORKERPOOL_NAME') | default('gpu', true) }}"
 
-
 # ROKS
 # -----------------------------------------------------------------------------
 ibmcloud_endpoint: "{{ lookup('env', 'IBMCLOUD_ENDPOINT') | default('https://cloud.ibm.com', true) }}"
@@ -38,7 +36,6 @@ roks_flavor: "{{ lookup('env', 'ROKS_FLAVOR') | default('b3c.16x64.300gb', true)
 roks_workers: "{{ lookup('env', 'ROKS_WORKERS') | default('3', true) }}"
 roks_flags: "{{ lookup('env', 'ROKS_FLAGS') | default('', true) }}"
 
-
 # FYRE
 # -----------------------------------------------------------------------------
 fyre_username: "{{ lookup('env', 'FYRE_USERNAME') }}"
@@ -54,14 +51,12 @@ fyre_worker_count: "{{ lookup('env', 'FYRE_WORKER_COUNT') | default('3', true) }
 fyre_worker_memory: "{{ lookup('env', 'FYRE_WORKER_MEMORY') | default('16', true) }}"
 fyre_worker_cpu: "{{ lookup('env', 'FYRE_WORKER_CPU') | default('64', true) }}"
 
-
 # ROSA
 # -----------------------------------------------------------------------------
 rosa_token: "{{ lookup('env', 'ROSA_TOKEN') }}"
 rosa_cluster_admin_password: "{{ lookup('env', 'ROSA_CLUSTER_ADMIN_PASSWORD') }}"
 rosa_compute_nodes: "{{ lookup('env', 'ROSA_COMPUTE_NODES') | default('3', true) }}"
 
-
 # AWS
 # -----------------------------------------------------------------------------
 aws_access_key_id: "{{ lookup('env', 'AWS_ACCESS_KEY_ID') }}"
@@ -93,4 +88,3 @@ ipi_config_dir: "{{ ipi_dir }}/config/{{ cluster_name }}"
 
 ocp_installer_dir: "{{ ipi_dir }}/installer/{{ ocp_version }}"
 ocp_installer_exe: "{{ ipi_dir }}/installer/{{ ocp_version }}/openshift-install"
-

ibm/mas_devops/roles/sls/tasks/install/main.yml

@@ -178,6 +178,7 @@
       password: "{{ mongocfg[0].data.password | b64decode}}"
       hosts: "{{ mongocfg[1].spec.config.hosts }}"
       certificates: "{{ lookup('template', 'templates/mongo-certificates.yml.j2') }}"
+  no_log: true
   when: mongocfg is defined and mongocfg[0] is defined and mongocfg[0].data is defined
 
 - name: Create the Mongo Secret for SLS

ibm/mas_devops/roles/suite_app_config/vars/assist.yml

@@ -2,5 +2,5 @@
 mas_app_ws_fqn: assistworkspaces.apps.mas.ibm.com
 mas_app_ws_apiversion: apps.mas.ibm.com/v1
 mas_app_ws_kind: AssistWorkspace
-mas_app_cfg_delay: 120
-mas_app_cfg_retries: 30
+mas_app_cfg_delay: "{{ lookup('env', 'MAS_APP_CFG_DELAY') | default(120, true)}}"
+mas_app_cfg_retries: "{{ lookup('env', 'MAS_APP_CFG_RETRIES') | default(30, true)}}"

ibm/mas_devops/roles/suite_app_config/vars/health.yml

@@ -3,8 +3,8 @@
 mas_app_ws_fqn: healthworkspaces.apps.mas.ibm.com
 mas_app_ws_apiversion: apps.mas.ibm.com/v1
 mas_app_ws_kind: HealthWorkspace
-mas_app_cfg_retries: 50
-mas_app_cfg_delay: 480
+mas_app_cfg_delay: "{{ lookup('env', 'MAS_APP_CFG_DELAY') | default(480, true)}}"
+mas_app_cfg_retries: "{{ lookup('env', 'MAS_APP_CFG_RETRIES') | default(50, true)}}"
 
 mas_app_settings_aio_flag: "{{ lookup('env', 'MAS_APP_SETTINGS_AIO_FLAG') | default('true', true)}}"
 mas_app_settings_db2_schema: "{{ lookup('env', 'MAS_APP_SETTINGS_DB2_SCHEMA') | default('maximo', true)}}"

ibm/mas_devops/roles/suite_app_config/vars/hputilities.yml

@@ -2,6 +2,5 @@
 mas_app_ws_fqn: hputilitiesworkspaces.apps.mas.ibm.com
 mas_app_ws_apiversion: apps.mas.ibm.com/v1
 mas_app_ws_kind: HPUtilitiesWorkspace
-
-mas_app_cfg_delay: 120
-mas_app_cfg_retries: 30
+mas_app_cfg_delay: "{{ lookup('env', 'MAS_APP_CFG_DELAY') | default(120, true)}}"
+mas_app_cfg_retries: "{{ lookup('env', 'MAS_APP_CFG_RETRIES') | default(30, true)}}"

ibm/mas_devops/roles/suite_app_config/vars/iot.yml

@@ -2,5 +2,5 @@
 mas_app_ws_fqn: iotworkspaces.iot.ibm.com
 mas_app_ws_apiversion: iot.ibm.com/v1
 mas_app_ws_kind: IoTWorkspace
-mas_app_cfg_delay: 120
-mas_app_cfg_retries: 30
+mas_app_cfg_delay: "{{ lookup('env', 'MAS_APP_CFG_DELAY') | default(120, true)}}"
+mas_app_cfg_retries: "{{ lookup('env', 'MAS_APP_CFG_RETRIES') | default(30, true)}}"

ibm/mas_devops/roles/suite_app_config/vars/manage.yml

@@ -4,8 +4,8 @@ mas_app_ws_apiversion: apps.mas.ibm.com/v1
 mas_app_ws_kind: ManageWorkspace
 
 # Depending on the number of components being used the time to configure Manage can grow significantly
-mas_app_cfg_retries: 60  # ~8 hours
-mas_app_cfg_delay: 480  # ~8 minutes
+mas_app_cfg_delay: "{{ lookup('env', 'MAS_APP_CFG_DELAY') | default(480, true)}}" # ~8 minutes
+mas_app_cfg_retries: "{{ lookup('env', 'MAS_APP_CFG_RETRIES') | default(60, true)}}" # ~8 hours
 
 mas_app_settings_aio_flag: "{{ lookup('env', 'MAS_APP_SETTINGS_AIO_FLAG') | default('true', true) | bool }}"
 mas_app_settings_db2_schema: "{{ lookup('env', 'MAS_APP_SETTINGS_DB2_SCHEMA') | default('maximo', true)}}"

ibm/mas_devops/roles/suite_app_config/vars/monitor.yml

@@ -3,5 +3,5 @@ mas_app_ws_fqn: monitorworkspaces.apps.mas.ibm.com
 mas_app_ws_apiversion: apps.mas.ibm.com/v1
 mas_app_ws_kind: MonitorWorkspace
 
-mas_app_cfg_delay: 120
-mas_app_cfg_retries: 30
+mas_app_cfg_delay: "{{ lookup('env', 'MAS_APP_CFG_DELAY') | default(120, true)}}"
+mas_app_cfg_retries: "{{ lookup('env', 'MAS_APP_CFG_RETRIES') | default(30, true)}}"

ibm/mas_devops/roles/suite_app_config/vars/mso.yml

@@ -3,5 +3,5 @@ mas_app_ws_fqn: msoworkspaces.apps.mas.ibm.com
 mas_app_ws_apiversion: apps.mas.ibm.com/v1
 mas_app_ws_kind: MSOWorkspace
 
-mas_app_cfg_delay: 120
-mas_app_cfg_retries: 30
+mas_app_cfg_delay: "{{ lookup('env', 'MAS_APP_CFG_DELAY') | default(120, true)}}"
+mas_app_cfg_retries: "{{ lookup('env', 'MAS_APP_CFG_RETRIES') | default(30, true)}}"

ibm/mas_devops/roles/suite_app_config/vars/optimizer.yml

@@ -3,5 +3,5 @@ mas_app_ws_fqn: optimizerworkspaces.apps.mas.ibm.com
 mas_app_ws_apiversion: apps.mas.ibm.com/v1
 mas_app_ws_kind: OptimizerWorkspace
 
-mas_app_cfg_delay: 120
-mas_app_cfg_retries: 30
+mas_app_cfg_delay: "{{ lookup('env', 'MAS_APP_CFG_DELAY') | default(120, true)}}"
+mas_app_cfg_retries: "{{ lookup('env', 'MAS_APP_CFG_RETRIES') | default(30, true)}}"

ibm/mas_devops/roles/suite_app_config/vars/predict.yml

@@ -3,5 +3,5 @@ mas_app_ws_fqn: predictworkspaces.apps.mas.ibm.com
 mas_app_ws_apiversion: apps.mas.ibm.com/v1
 mas_app_ws_kind: PredictWorkspace
 
-mas_app_cfg_delay: 120
-mas_app_cfg_retries: 30
+mas_app_cfg_delay: "{{ lookup('env', 'MAS_APP_CFG_DELAY') | default(120, true)}}"
+mas_app_cfg_retries: "{{ lookup('env', 'MAS_APP_CFG_RETRIES') | default(30, true)}}"

ibm/mas_devops/roles/suite_app_config/vars/safety.yml

@@ -3,5 +3,5 @@ mas_app_ws_fqn: safetyworkspaces.apps.mas.ibm.com
 mas_app_ws_apiversion: apps.mas.ibm.com/v1
 mas_app_ws_kind: SafetyWorkspace
 
-mas_app_cfg_delay: 120
-mas_app_cfg_retries: 30
+mas_app_cfg_delay: "{{ lookup('env', 'MAS_APP_CFG_DELAY') | default(120, true)}}"
+mas_app_cfg_retries: "{{ lookup('env', 'MAS_APP_CFG_RETRIES') | default(30, true)}}"

ibm/mas_devops/roles/suite_app_config/vars/visualinspection.yml

@@ -3,5 +3,5 @@ mas_app_ws_fqn: visualinspectionappworkspaces.apps.mas.ibm.com
 mas_app_ws_apiversion: apps.mas.ibm.com/v1
 mas_app_ws_kind: VisualInspectionAppWorkspace
 
-mas_app_cfg_delay: 120
-mas_app_cfg_retries: 30
+mas_app_cfg_delay: "{{ lookup('env', 'MAS_APP_CFG_DELAY') | default(120, true)}}"
+mas_app_cfg_retries: "{{ lookup('env', 'MAS_APP_CFG_RETRIES') | default(30, true)}}"