Merge branch 'master' into alexy_logging

.zuul.yaml

@@ -28,7 +28,7 @@
         override-checkout: main
       - name: github.com/openstack-k8s-operators/telemetry-operator
         override-checkout: main
-    irrelevant-files:
+    irrelevant-files: &irrelevant_files
       - .github/.*
       - ci/github/.*
       - callback_plugins/.*
@@ -63,17 +63,22 @@
         override-checkout: main
       - name: github.com/openstack-k8s-operators/telemetry-operator
         override-checkout: main
-    irrelevant-files:
-      - .github/.*
-      - ci/github/.*
-      - callback_plugins/.*
-      - README*
-      - .*/*.md
+    irrelevant-files: *irrelevant_files      
+
+    name: feature-verification-tests-noop
+    parent: noop
+    description: |
+      A job that always passes. Runs when there's a change to jobs that don't
+      need full zuul to run but still need to report a pass.
+    run:
+      - ci/noop.yml
+    files: *irrelevant_files
 
 - project:
     name: infrawatch/feature-verification-tests
     github-check:
       jobs:
+        - feature-verification-tests-noop
         - openstack-k8s-operators-content-provider:
             override-checkout: main
         - functional-tests-on-osp18

ci/github/test_logger.yml

@@ -36,3 +36,9 @@
       when: true
       fail:
         msg: "If the task fails, the status will be reported since there's a test ID."
+
+    - name: "Set the name based on a var input"
+      set_fact:
+        testid: "RHOSO-1234"
+    - name: "run test with variable name - {{ testid }}"
+      debug: msg="test"

ci/github/test_logger_expected

@@ -6,3 +6,4 @@ RHELOSP-042=passed
 RHELOSP-043=passed
 RHELOSP-054=passed
 RHOSO-078=failed
+RHOSO-1234=passed

ci/noop.yml

@@ -0,0 +1,5 @@
+---
+- hosts: localhost
+  tasks:
+    - ansible.builtin.debug:
+        msg: "Do nothing"

ci/run_playbooks.yml

@@ -67,8 +67,6 @@
           tags:
             - setup
 
-    - name: Run telemetry tests on OSP18
-      block:
         - name: "Run telemetry tests playbook locally on the target host"
           ansible.builtin.shell:
             cmd: |
@@ -80,13 +78,12 @@
           ansible.builtin.copy:
             content: "{{ output.stdout }}"
             dest: "{{ logs_dir }}/ansible_run.log"
-
-
-    - name: Revert the version update
-      ansible.builtin.shell:
-        cmd: |
-          oc patch  openstackversions controlplane  --type json -p='[{"op": "replace", "path": "/spec/customContainerImages", "value": {} }]'
-      when: "{{ patch_openstackversions | bool }}"
+      always:
+        - name: Revert the version update
+          ansible.builtin.shell:
+            cmd: |
+              oc patch  openstackversions controlplane  --type json -p='[{"op": "replace", "path": "/spec/customContainerImages", "value": {} }]'
+          when: "{{ patch_openstackversions | bool }}"
 
     - name: Include report result 
       ansible.builtin.include_tasks:

roles/telemetry_autoscaling/README.md

@@ -7,11 +7,29 @@ Requirements
 ------------
 The following resources are required in the OpenStack cloud
 * network called public
-* network called provate
+* network called private
 * security group called basic with ssh and tcp enabled to the VMs
 * a flavor called m1.small
 * an image called cirros
 
+Tests:
+------
+Verify overcloud deployment for autoscaling
+    Test service API endpoints
+    Verify all the services are running on overcloud
+    Verify time-series database service is available
+Using the heat service for autoscaling
+    Create an archive policy
+    Configure heat template for automatically scaling instances
+    Create the deployment template for heat to control instance scaling
+Create stack deployment for autoscaling
+    Verify that the stack and resources are created
+    Verify that the alarms were created for the stack
+    Verify the deployment and metric resources exist for the stack
+Testing and troubleshooting autoscaling
+    Verify that alarms are triggered with traffic
+    Verify that Orchestration service has scaled the instances
+
 Role Variables
 --------------
 

roles/telemetry_autoscaling/tasks/main.yml

@@ -10,6 +10,12 @@
   include_vars: "{{ item }}"
   with_items: "{{ vars_files }}"
 
+- name: RHOSO-12666 Test services are enabled for autoscaling
+  when: metrics_backend == "prometheus"
+  ansible.builtin.include_tasks: 
+    file: test_services.yml
+  tags: precheck
+
 - name: Check pre-reqs for autoscaling
   ansible.builtin.include_tasks: 
     file: verify_autoscaling.yml

roles/telemetry_autoscaling/tasks/test_services.yml

@@ -0,0 +1,35 @@
+---
+# Verify Orchestration (heat) and telemetry services resources are ready for autoscaling
+
+- name: Verify that custom resource HEAT is ready
+  ansible.builtin.command:
+    cmd: |
+      oc get heat heat -o jsonpath='{.status.conditions[?(@.type=="Ready")].status}{"\n"}'
+  register: result
+  failed_when:
+    - result.stdout != "True"
+
+- name: Verify that custom resource CEILOMETER is ready
+  ansible.builtin.command:
+    cmd: |
+      oc get ceilometer ceilometer -o jsonpath='{.status.conditions[?(@.type=="Ready")].status}{"\n"}'
+  register: result
+  failed_when:
+    - result.stdout != "True"
+
+# - name: Verify that custom resource AUTOSCALING is ready
+# It is returning an unexpected response and needs further debugging. will raise another PR to inspect this
+#   ansible.builtin.command:
+#     cmd: |
+#       oc get autoscaling autoscaling -o jsonpath='{.status.conditions[?(@.type=="Ready")].status}{"\n"}'
+#   register: result
+#   failed_when:
+#     - result.stdout != "True"
+
+- name: Verify that custom resource METRICSTORAGE is ready
+  ansible.builtin.command:
+    cmd: |
+      oc get metricstorage metric-storage -o jsonpath='{.status.conditions[?(@.type=="Ready")].status}{"\n"}'
+  register: result
+  failed_when:
+    - result.stdout != "True"

roles/telemetry_autoscaling/tasks/verify_autoscaling.yml

@@ -40,3 +40,12 @@
     {{ openstack_cmd }} metric status --fit-width;
   register: result
   failed_when: result.rc >= 1
+
+# This works when using prometheus as the metrics backend
+- name: Verify that PROMETHEUS is enabled
+  when: metrics_backend == "prometheus"
+  ansible.builtin.shell: |
+    {{ openstack_cmd }} metric query up  --disable-rbac -c container -c value |grep -i "prometheus" |awk '{print $4}'
+  register: result
+  failed_when:
+    - result.stdout != "0"

roles/telemetry_logging/README.md

@@ -0,0 +1,53 @@
+telemetry_logging
+=========
+
+Test logging in Openstack
+
+Requirements
+------------
+
+Role Variables
+--------------
+
+  For journal_tests.yml
+
+    identifiers_test_id
+      - polarion id for test
+    identifiers_list  
+      - Lists identifier strings to look for in the journalctl of the compute nodes
+
+
+Dependencies
+------------
+
+Openstack on Openshift deployed and logging enabled for Openstack
+
+Example Playbook
+----------------
+
+Each tasks/playbook.yml should be called independently via "ansible.builtin.import_role" with appropriate vars passed:
+
+- name: "Verify logging journalctl identifiers" 
+  hosts: computes
+  gather_facts: no
+  vars:
+    identifiers_test_id: "RHOSO-12681"
+    identifiers_list:
+      - ceilometer_agent_compute
+      - nova_compute
+
+  tasks:
+    - name: "Verify journalctl logging identifiers" 
+      ansible.builtin.import_role:
+        name: telemetry_logging
+
+
+License
+-------
+
+Apache 2
+
+Author Information
+------------------
+
+An optional section for the role authors to include contact information, or a website (HTML is not allowed).

roles/telemetry_logging/meta/main.yml

@@ -0,0 +1,53 @@
+---
+galaxy_info:
+  author: Alex Yefimov
+  description: Tests that logging is set up as expected in OpenSTack running on OpenShift
+  company: Red Hat
+
+  # If the issue tracker for your role is not on github, uncomment the
+  # next line and provide a value
+  # issue_tracker_url: http://example.com/issue/tracker
+
+  # Choose a valid license ID from https://spdx.org - some suggested licenses:
+  # - BSD-3-Clause (default)
+  # - MIT
+  # - GPL-2.0-or-later
+  # - GPL-3.0-only
+  # - Apache-2.0
+  # - CC-BY-4.0
+  license: Apache-2.0
+
+  min_ansible_version: "2.1"
+
+  # If this a Container Enabled role, provide the minimum Ansible Container version.
+  # min_ansible_container_version:
+
+  #
+  # Provide a list of supported platforms, and for each platform a list of versions.
+  # If you don't wish to enumerate all versions for a particular platform, use 'all'.
+  # To view available platforms and versions (or releases), visit:
+  # https://galaxy.ansible.com/api/v1/platforms/
+  #
+  # platforms:
+  # - name: Fedora
+  #   versions:
+  #   - all
+  #   - 25
+  # - name: SomePlatform
+  #   versions:
+  #   - all
+  #   - 1.0
+  #   - 7
+  #   - 99.99
+
+  galaxy_tags: []
+    # List tags for your role here, one per line. A tag is a keyword that describes
+    # and categorizes the role. Users find roles by searching for tags. Be sure to
+    # remove the '[]' above, if you add tags to this list.
+    #
+    # NOTE: A tag is limited to a single word comprised of alphanumeric characters.
+    #       Maximum 20 tags per role.
+
+dependencies: []
+  # List your role dependencies here, one per line. Be sure to remove the '[]' above,
+  # if you add dependencies to this list.

roles/telemetry_logging/tasks/journal_tests.yml

@@ -0,0 +1,10 @@
+---
+- name: Get journals
+  ansible.builtin.shell:
+    cmd:
+      tstamp=$(date -d '30 minute ago' "+%Y-%m-%d %H:%M:%S")
+      journalctl -t "{{ item }}" --no-pager -S "${tstamp}" | wc -l
+  register: journal_wc
+  changed_when: false
+  failed_when:  
+    - journal_wc.stdout | int <= 1

roles/telemetry_logging/tasks/main.yml

@@ -0,0 +1,5 @@
+---
+- name: "Verify journal entries - {{ journal_test_id }}"
+  when: journal_list is defined
+  ansible.builtin.include_tasks: "journal_tests.yml"
+  loop: "{{ identifiers_list }}"