Merge "pre-commit: Integrate bandit"

This change added the prelude for the 2025.1 Expoxy release cycle.

Change-Id: I8223842a57491a91c565e47bd1819db4d142e628

.pre-commit-config.yaml

@@ -0,0 +1,62 @@
+---
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      # whitespace
+      - id: trailing-whitespace
+      - id: mixed-line-ending
+        args: ['--fix', 'lf']
+        exclude: '.*\.(svg)$'
+      - id: check-byte-order-marker
+      # file format and permissions
+      - id: check-ast
+      - id: debug-statements
+      - id: check-json
+        files: .*\.json$
+      - id: check-yaml
+        files: .*\.(yaml|yml)$
+      - id: check-executables-have-shebangs
+      - id: check-shebang-scripts-are-executable
+      # git
+      - id: check-added-large-files
+      - id: check-case-conflict
+      - id: detect-private-key
+      - id: check-merge-conflict
+  - repo: https://github.com/Lucas-C/pre-commit-hooks
+    rev: v1.5.5
+    hooks:
+      - id: remove-tabs
+        exclude: '.*\.(svg)$'
+  - repo: https://opendev.org/openstack/hacking
+    rev: 7.0.0
+    hooks:
+      - id: hacking
+        additional_dependencies: []
+        exclude: '^(doc|releasenotes|tools)/.*$'
+  - repo: https://github.com/PyCQA/bandit
+    rev: 1.7.6
+    hooks:
+      - id: bandit
+        args: ['-x', 'tests', '-s', 'B101,B311,B320']
+  - repo: https://github.com/hhatto/autopep8
+    rev: v2.3.1
+    hooks:
+      - id: autopep8
+        files: '^.*\.py$'
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.3.0
+    hooks:
+      - id: codespell
+        args: ['--ignore-words=doc/dictionary.txt']
+  - repo: https://github.com/sphinx-contrib/sphinx-lint
+    rev: v1.0.0
+    hooks:
+      - id: sphinx-lint
+        args: [--enable=default-role]
+        files: ^doc/|releasenotes|api-guide
+        types: [rst]
+  - repo: https://github.com/PyCQA/doc8
+    rev: v1.1.2
+    hooks:
+      - id: doc8

.zuul.yaml

@@ -9,76 +9,25 @@
     check:
       jobs:
         - watcher-tempest-functional
+        - watcher-tempest-functional-jammy
         - watcher-grenade
         - watcher-tempest-strategies
         - watcher-tempest-actuator
         - watcherclient-tempest-functional
         - watcher-tempest-functional-ipv6-only
+        - watcher-prometheus-integration
     gate:
       jobs:
         - watcher-tempest-functional
+        - watcher-tempest-functional-jammy
         - watcher-tempest-functional-ipv6-only
 
-- job:
-    name: watcher-tempest-dummy_optim
-    parent: watcher-tempest-multinode
-    vars:
-      tempest_test_regex: watcher_tempest_plugin.tests.scenario.test_execute_dummy_optim
-
 - job:
     name: watcher-tempest-actuator
     parent: watcher-tempest-multinode
     vars:
       tempest_test_regex: watcher_tempest_plugin.tests.scenario.test_execute_actuator
 
-- job:
-    name: watcher-tempest-basic_optim
-    parent: watcher-tempest-multinode
-    vars:
-      tempest_test_regex: watcher_tempest_plugin.tests.scenario.test_execute_basic_optim
-
-- job:
-    name: watcher-tempest-vm_workload_consolidation
-    parent: watcher-tempest-multinode
-    vars:
-      tempest_test_regex: watcher_tempest_plugin.tests.scenario.test_execute_vm_workload_consolidation
-      devstack_local_conf:
-        test-config:
-          $WATCHER_CONFIG:
-            watcher_strategies.vm_workload_consolidation:
-              datasource: ceilometer
-
-- job:
-    name: watcher-tempest-workload_balancing
-    parent: watcher-tempest-multinode
-    vars:
-      tempest_test_regex: watcher_tempest_plugin.tests.scenario.test_execute_workload_balancing
-
-- job:
-    name: watcher-tempest-zone_migration
-    parent: watcher-tempest-multinode
-    vars:
-      tempest_test_regex: watcher_tempest_plugin.tests.scenario.test_execute_zone_migration
-
-- job:
-    name: watcher-tempest-host_maintenance
-    parent: watcher-tempest-multinode
-    vars:
-      tempest_test_regex: watcher_tempest_plugin.tests.scenario.test_execute_host_maintenance
-
-- job:
-    name: watcher-tempest-storage_balance
-    parent: watcher-tempest-multinode
-    vars:
-      tempest_test_regex: watcher_tempest_plugin.tests.scenario.test_execute_storage_balance
-      devstack_local_conf:
-        test-config:
-          $TEMPEST_CONFIG:
-            volume:
-              backend_names: ['BACKEND_1', 'BACKEND_2']
-            volume-feature-enabled:
-              multi_backend: true
-
 - job:
     name: watcher-tempest-strategies
     parent: watcher-tempest-multinode
@@ -89,7 +38,7 @@
 - job:
     name: watcher-tempest-multinode
     parent: watcher-tempest-functional
-    nodeset: openstack-two-node-focal
+    nodeset: openstack-two-node-noble
     roles:
       - zuul: openstack/tempest
     group-vars:
@@ -107,6 +56,7 @@
           watcher-api: false
           watcher-decision-engine: true
           watcher-applier: false
+          c-bak: false
           ceilometer: false
           ceilometer-acompute: false
           ceilometer-acentral: false
@@ -169,6 +119,17 @@
       zuul_copy_output:
         /etc/hosts: logs
 
+# TODO(gmann): As per the 2025.1 testing runtime, we need to run at least
+# one job on jammy. This job can be removed in the next cycle(2025.2)
+- job:
+    name: watcher-tempest-functional-jammy
+    description: This is integrated job testing on Ubuntu jammy(22.04)
+    parent: watcher-tempest-functional
+    nodeset: openstack-single-node-jammy
+    vars:
+      <<: *base_vars
+      python_version: '3.9'
+
 - job:
     name: watcher-tempest-functional-ipv6-only
     parent: devstack-tempest-ipv6
@@ -185,7 +146,7 @@
       - openstack/python-watcherclient
       - openstack/watcher-tempest-plugin
     vars: *base_vars
-    irrelevant-files:
+    irrelevant-files: &irrelevent_files
       - ^(test-|)requirements.txt$
       - ^.*\.rst$
       - ^api-ref/.*$
@@ -205,3 +166,124 @@
     vars:
       tempest_concurrency: 1
       tempest_test_regex: watcher_tempest_plugin.tests.client_functional
+
+- job:
+    name: watcher-sg-core-tempest-base
+    parent: devstack-tempest
+    nodeset: openstack-two-node-noble
+    description: |
+      This job is for testing watcher and sg-core/prometheus installation
+    abstract: true
+    pre-run:
+      - playbooks/generate_prometheus_config.yml
+    irrelevant-files: *irrelevent_files
+    timeout: 7800
+    required-projects: &base_sg_required_projects
+      - openstack/aodh
+      - openstack/ceilometer
+      - openstack/tempest
+      - openstack-k8s-operators/sg-core
+      - openstack/watcher
+      - openstack/python-watcherclient
+      - openstack/watcher-tempest-plugin
+      - openstack/devstack-plugin-prometheus
+    vars:
+      configure_swap_size: 8192
+      devstack_plugins:
+        ceilometer: https://opendev.org/openstack/ceilometer
+        aodh: https://opendev.org/openstack/aodh
+        sg-core: https://github.com/openstack-k8s-operators/sg-core
+        watcher: https://opendev.org/openstack/watcher
+        devstack-plugin-prometheus: https://opendev.org/openstack/devstack-plugin-prometheus
+      devstack_services:
+        watcher-api: true
+        watcher-decision-engine: true
+        watcher-applier: true
+        tempest: true
+        # We do not need Swift in this job so disable it for speed
+        # Swift services
+        s-account: false
+        s-container: false
+        s-object: false
+        s-proxy: false
+        # Prometheus related service
+        prometheus: true
+        node_exporter: true
+      devstack_localrc:
+        CEILOMETER_BACKENDS: "sg-core"
+        CEILOMETER_PIPELINE_INTERVAL: 15
+        CEILOMETER_ALARM_THRESHOLD: 6000000000
+        NODE_EXPORTER_ENABLE: false
+        PROMETHEUS_ENABLE: false
+        PROMETHEUS_SERVICE_SCRAPE_TARGETS: "sg-core,node-exporter"
+        PROMETHEUS_CONFIG_FILE: "/home/zuul/prometheus.yml"
+      devstack_local_conf:
+        post-config:
+          $WATCHER_CONF:
+            watcher_datasources:
+              datasources: prometheus
+            prometheus_client:
+              host: 127.0.0.1
+              port: 9090
+            watcher_cluster_data_model_collectors.compute:
+              period: 120
+            watcher_cluster_data_model_collectors.baremetal:
+              period: 120
+            watcher_cluster_data_model_collectors.storage:
+              period: 120
+        test-config:
+          $TEMPEST_CONFIG:
+            compute:
+              min_compute_nodes: 2
+              min_microversion: 2.56
+            compute-feature-enabled:
+              live_migration: true
+              block_migration_for_live_migration: true
+            placement:
+              min_microversion: 1.29
+            service_available:
+              sg_core: True
+            telemetry_services:
+              metric_backends: prometheus
+            telemetry:
+              disable_ssl_certificate_validation: True
+              ceilometer_polling_interval: 15
+            optimize:
+              datasource: prometheus
+      tempest_plugins:
+        - watcher-tempest-plugin
+      tempest_test_regex: watcher_tempest_plugin.tests.scenario.test_execute_strategies
+      tempest_concurrency: 1
+      tox_envlist: all
+      zuul_copy_output:
+        /etc/prometheus/prometheus.yml: logs
+    group-vars:
+      subnode:
+        devstack_plugins:
+          ceilometer: https://opendev.org/openstack/ceilometer
+          sg-core: https://github.com/openstack-k8s-operators/sg-core
+          devstack-plugin-prometheus: https://opendev.org/openstack/devstack-plugin-prometheus
+        devstack_services:
+          ceilometer-acompute: true
+          sg-core: false
+          prometheus: false
+          node_exporter: true
+        devstack_localrc:
+          CEILOMETER_BACKEND: "none"
+          CEILOMETER_BACKENDS: "none"
+          # sg_core related var
+          NODE_EXPORTER_ENABLE: false
+          PROMETHEUS_ENABLE: false
+        devstack_local_conf:
+          post-config:
+            $WATCHER_CONF:
+              watcher_cluster_data_model_collectors.compute:
+                period: 120
+              watcher_cluster_data_model_collectors.baremetal:
+                period: 120
+              watcher_cluster_data_model_collectors.storage:
+                period: 120
+
+- job:
+    name: watcher-prometheus-integration
+    parent: watcher-sg-core-tempest-base

api-ref/source/samples/audit-list-detailed-response.json

@@ -30,7 +30,7 @@
                 }
             },
             "auto_trigger": false,
-	    "force": false,
+            "force": false,
             "uuid": "65a5da84-5819-4aea-8278-a28d2b489028",
             "goal_name": "workload_balancing",
             "scope": [],

api-ref/source/samples/datamodel-list-response.json

@@ -13,9 +13,9 @@
             "node_vcpu_ratio": "16.0",
             "node_memory": "16383",
             "node_memory_ratio": "1.5",
-            "node_disk": "37"
+            "node_disk": "37",
             "node_disk_ratio": "1.0",
-            "node_state": "up",
+            "node_state": "up"
         },
         {
             "server_uuid": "e2cb5f6f-fa1d-4ba2-be1e-0bf02fa86ba4",
@@ -30,9 +30,9 @@
             "node_vcpu_ratio": "16.0",
             "node_memory": "16383",
             "node_memory_ratio": "1.5",
-            "node_disk": "37"
+            "node_disk": "37",
             "node_disk_ratio": "1.0",
-            "node_state": "up",
+            "node_state": "up"
         }
     ]
 }

api-ref/source/watcher-api-v1-goals.inc

@@ -12,7 +12,7 @@ Here are some examples of ``Goals``:
 -  minimize the energy consumption
 -  minimize the number of compute nodes (consolidation)
 -  balance the workload among compute nodes
--  minimize the license cost (some softwares have a licensing model which is
+-  minimize the license cost (some software have a licensing model which is
    based on the number of sockets or cores where the software is deployed)
 -  find the most appropriate moment for a planned maintenance on a
    given group of host (which may be an entire availability zone):
@@ -123,4 +123,4 @@ Response
 **Example JSON representation of a Goal:**
 
 .. literalinclude:: samples/goal-show-response.json
-   :language: javascript
+   :language: javascript

devstack/lib/watcher

@@ -1,5 +1,3 @@
-#!/bin/bash
-#
 # lib/watcher
 # Functions to control the configuration and operation of the watcher services
 
@@ -38,7 +36,6 @@ GITBRANCH["python-watcherclient"]=${WATCHERCLIENT_BRANCH:-master}
 GITDIR["python-watcherclient"]=$DEST/python-watcherclient
 
 WATCHER_STATE_PATH=${WATCHER_STATE_PATH:=$DATA_DIR/watcher}
-WATCHER_AUTH_CACHE_DIR=${WATCHER_AUTH_CACHE_DIR:-/var/cache/watcher}
 
 WATCHER_CONF_DIR=/etc/watcher
 WATCHER_CONF=$WATCHER_CONF_DIR/watcher.conf
@@ -103,7 +100,7 @@ function _cleanup_watcher_apache_wsgi {
 # cleanup_watcher() - Remove residual data files, anything left over from previous
 # runs that a clean run would need to clean up
 function cleanup_watcher {
-    sudo rm -rf $WATCHER_STATE_PATH $WATCHER_AUTH_CACHE_DIR
+    sudo rm -rf $WATCHER_STATE_PATH
     if [[ "$WATCHER_USE_WSGI_MODE" == "uwsgi" ]]; then
         remove_uwsgi_config "$WATCHER_UWSGI_CONF" "$WATCHER_UWSGI"
     else
@@ -210,8 +207,8 @@ function create_watcher_conf {
 
     iniset $WATCHER_CONF oslo_messaging_notifications driver "messagingv2"
 
-    configure_auth_token_middleware $WATCHER_CONF watcher $WATCHER_AUTH_CACHE_DIR
+    configure_keystone_authtoken_middleware $WATCHER_CONF watcher
-    configure_auth_token_middleware $WATCHER_CONF watcher $WATCHER_AUTH_CACHE_DIR "watcher_clients_auth"
+    configure_keystone_authtoken_middleware $WATCHER_CONF watcher "watcher_clients_auth"
 
     if is_fedora || is_suse; then
         # watcher defaults to /usr/local/bin, but fedora and suse pip like to
@@ -248,13 +245,6 @@ function create_watcher_conf {
     fi
 }
 
-# create_watcher_cache_dir() - Part of the init_watcher() process
-function create_watcher_cache_dir {
-    # Create cache dir
-    sudo install -d -o $STACK_USER $WATCHER_AUTH_CACHE_DIR
-    rm -rf $WATCHER_AUTH_CACHE_DIR/*
-}
-
 # init_watcher() - Initialize databases, etc.
 function init_watcher {
     # clean up from previous (possibly aborted) runs
@@ -266,7 +256,6 @@ function init_watcher {
         # Create watcher schema
         $WATCHER_BIN_DIR/watcher-db-manage --config-file $WATCHER_CONF upgrade
     fi
-    create_watcher_cache_dir
 }
 
 # install_watcherclient() - Collect source and prepare
@@ -275,6 +264,9 @@ function install_watcherclient {
         git_clone_by_name "python-watcherclient"
         setup_dev_lib "python-watcherclient"
     fi
+    if [[ "$GLOBAL_VENV" == "True" ]]; then
+        sudo ln -sf /opt/stack/data/venv/bin/watcher /usr/local/bin
+    fi
 }
 
 # install_watcher() - Collect source and prepare

devstack/plugin.sh

@@ -1,5 +1,3 @@
-#!/bin/bash
-#
 # plugin.sh - DevStack plugin script to install watcher
 
 # Save trace setting

devstack/upgrade/from_rocky/upgrade-watcher

@@ -1,5 +1,3 @@
-#!/usr/bin/env bash
-
 # ``upgrade-watcher``
 
 function configure_watcher_upgrade {

devstack/upgrade/upgrade.sh

@@ -70,7 +70,7 @@ then write_uwsgi_config "$WATCHER_UWSGI_CONF" "$WATCHER_UWSGI" "/infra-optim"
 fi
 
 # Migrate the database
-watcher-db-manage upgrade || die $LINO "DB migration error"
+$WATCHER_BIN_DIR/watcher-db-manage upgrade || die $LINO "DB migration error"
 
 start_watcher
 

doc/dictionary.txt

@@ -0,0 +1,4 @@
+thirdparty
+assertin
+notin
+

doc/ext/term.py

@@ -52,7 +52,7 @@ class BaseWatcherDirective(rst.Directive):
                 obj_raw_docstring = obj.__init__.__doc__
 
         if not obj_raw_docstring:
-            # Raise a warning to make the tests fail wit doc8
+            # Raise a warning to make the tests fail with doc8
             raise self.error("No docstring available for %s!" % obj)
 
         obj_docstring = inspect.cleandoc(obj_raw_docstring)

doc/requirements.txt

@@ -1,10 +1,10 @@
-# The order of packages is significant, because pip processes them in the order
+sphinx>=2.1.1 # BSD
-# of appearance. Changing the order has an impact on the overall integration
-# process, which may cause wedges in the gate later.
-openstackdocstheme>=2.2.1 # Apache-2.0
-sphinx>=2.0.0,!=2.1.0 # BSD
-sphinxcontrib-pecanwsme>=0.8.0 # Apache-2.0
 sphinxcontrib-svg2pdfconverter>=0.1.0 # BSD
-reno>=3.1.0 # Apache-2.0
+sphinxcontrib-pecanwsme>=0.8.0 # Apache-2.0
 sphinxcontrib-apidoc>=0.2.0  # BSD
+# openstack
 os-api-ref>=1.4.0 # Apache-2.0
+openstackdocstheme>=2.2.1 # Apache-2.0
+# releasenotes
+reno>=3.1.0 # Apache-2.0
+

doc/source/admin/gmr.rst

@@ -34,7 +34,7 @@ own sections.  However, the base *GMR* consists of several sections:
 
 Package
   Shows information about the package to which this process belongs, including
-  version informations.
+  version information.
 
 Threads
   Shows stack traces and thread ids for each of the threads within this

doc/source/architecture.rst

@@ -285,7 +285,7 @@ Audit and interval (in case of CONTINUOUS type). There is three types of Audit:
 ONESHOT, CONTINUOUS and EVENT. ONESHOT Audit is launched once and if it
 succeeded executed new action plan list will be provided; CONTINUOUS Audit
 creates action plans with specified interval (in seconds or cron format, cron
-inteval can be used like: `*/5 * * * *`), if action plan
+interval can be used like: ``*/5 * * * *``), if action plan
 has been created, all previous action plans get CANCELLED state;
 EVENT audit is launched when receiving webhooks API.
 

doc/source/conf.py

@@ -115,7 +115,7 @@ html_theme = 'openstackdocs'
 htmlhelp_basename = '%sdoc' % project
 
 
-#openstackdocstheme options
+# openstackdocstheme options
 openstackdocs_repo_name = 'openstack/watcher'
 openstackdocs_pdf_link = True
 openstackdocs_auto_name = False

doc/source/configuration/configuring.rst

@@ -194,11 +194,14 @@ The configuration file is organized into the following sections:
 * ``[watcher_applier]`` - Watcher Applier module configuration
 * ``[watcher_decision_engine]`` - Watcher Decision Engine module configuration
 * ``[oslo_messaging_rabbit]`` - Oslo Messaging RabbitMQ driver configuration
-* ``[ceilometer_client]`` - Ceilometer client configuration
 * ``[cinder_client]`` - Cinder client configuration
 * ``[glance_client]`` - Glance client configuration
+* ``[gnocchi_client]`` - Gnocchi client configuration
+* ``[ironic_client]`` - Ironic client configuration
+* ``[keystone_client]`` - Keystone client configuration
 * ``[nova_client]`` - Nova client configuration
 * ``[neutron_client]`` - Neutron client configuration
+* ``[placement_client]`` - Placement client configuration
 
 The Watcher configuration file is expected to be named
 ``watcher.conf``. When starting Watcher, you can specify a different
@@ -372,7 +375,7 @@ You can configure and install Ceilometer by following the documentation below :
 #. https://docs.openstack.org/ceilometer/latest
 
 The built-in strategy 'basic_consolidation' provided by watcher requires
-"**compute.node.cpu.percent**" and "**cpu_util**" measurements to be collected
+"**compute.node.cpu.percent**" and "**cpu**" measurements to be collected
 by Ceilometer.
 The measurements available depend on the hypervisors that OpenStack manages on
 the specific implementation.

doc/source/contributor/concurrency.rst

@@ -221,7 +221,7 @@ workflow engine can halt or take other actions while the action plan is being
 executed based on the success or failure of individual actions. However, the
 base workflow engine simply uses these notifies to store the result of
 individual actions in the database. Additionally, since taskflow uses a graph
-flow if any of the tasks would fail all childs of this tasks not be executed
+flow if any of the tasks would fail all children of this tasks not be executed
 while ``do_revert`` will be triggered for all parents.
 
 .. code-block:: python

doc/source/contributor/devstack.rst

@@ -16,7 +16,7 @@ multinode environment to use.
 You can set up the Watcher services quickly and easily using a Watcher
 DevStack plugin. See `PluginModelDocs`_ for information on DevStack's plugin
 model. To enable the Watcher plugin with DevStack, add the following to the
-`[[local|localrc]]` section of your controller's `local.conf` to enable the
+``[[local|localrc]]`` section of your controller's ``local.conf`` to enable the
 Watcher plugin::
 
     enable_plugin watcher https://opendev.org/openstack/watcher
@@ -32,7 +32,7 @@ Quick Devstack Instructions with Datasources
 
 Watcher requires a datasource to collect metrics from compute nodes and
 instances in order to execute most strategies. To enable this a
-`[[local|localrc]]` to setup DevStack for some of the supported datasources
+``[[local|localrc]]`` to setup DevStack for some of the supported datasources
 is provided. These examples specify the minimal configuration parameters to
 get both Watcher and the datasource working but can be expanded is desired.
 
@@ -41,54 +41,60 @@ Gnocchi
 
 With the Gnocchi datasource most of the metrics for compute nodes and
 instances will work with the provided configuration but metrics that
-require Ironic such as `host_airflow and` `host_power` will still be
+require Ironic such as ``host_airflow and`` ``host_power`` will still be
-unavailable as well as `instance_l3_cpu_cache`::
+unavailable as well as ``instance_l3_cpu_cache``
 
-        [[local|localrc]]
+.. code-block:: ini
-        enable_plugin watcher https://opendev.org/openstack/watcher
 
-        enable_plugin watcher-dashboard https://opendev.org/openstack/watcher-dashboard
+   [[local|localrc]]
 
-        enable_plugin ceilometer https://opendev.org/openstack/ceilometer.git
+   enable_plugin watcher https://opendev.org/openstack/watcher
-        CEILOMETER_BACKEND=gnocchi
+   enable_plugin watcher-dashboard https://opendev.org/openstack/watcher-dashboard
+   enable_plugin ceilometer https://opendev.org/openstack/ceilometer.git
+   enable_plugin aodh https://opendev.org/openstack/aodh
+   enable_plugin panko https://opendev.org/openstack/panko
 
-        enable_plugin aodh https://opendev.org/openstack/aodh
+   CEILOMETER_BACKEND=gnocchi
-        enable_plugin panko https://opendev.org/openstack/panko
+   [[post-config|$NOVA_CONF]]
-
+   [DEFAULT]
-        [[post-config|$NOVA_CONF]]
+   compute_monitors=cpu.virt_driver
-        [DEFAULT]
-        compute_monitors=cpu.virt_driver
 
 Detailed DevStack Instructions
 ==============================
 
-#. Obtain N (where N >= 1) servers (virtual machines preferred for DevStack).
+#.  Obtain N (where N >= 1) servers (virtual machines preferred for DevStack).
-   One of these servers will be the controller node while the others will be
+    One of these servers will be the controller node while the others will be
-   compute nodes. N is preferably >= 3 so that you have at least 2 compute
+    compute nodes. N is preferably >= 3 so that you have at least 2 compute
-   nodes, but in order to stand up the Watcher services only 1 server is
+    nodes, but in order to stand up the Watcher services only 1 server is
-   needed (i.e., no computes are needed if you want to just experiment with
+    needed (i.e., no computes are needed if you want to just experiment with
-   the Watcher services). These servers can be VMs running on your local
+    the Watcher services). These servers can be VMs running on your local
-   machine via VirtualBox if you prefer. DevStack currently recommends that
+    machine via VirtualBox if you prefer. DevStack currently recommends that
-   you use Ubuntu 16.04 LTS. The servers should also have connections to the
+    you use Ubuntu 16.04 LTS. The servers should also have connections to the
-   same network such that they are all able to communicate with one another.
+    same network such that they are all able to communicate with one another.
 
-#. For each server, clone the DevStack repository and create the stack user::
+#. For each server, clone the DevStack repository and create the stack user
 
-       sudo apt-get update
+   .. code-block:: bash
-       sudo apt-get install git
+
-       git clone https://opendev.org/openstack/devstack.git
+        sudo apt-get update
-       sudo ./devstack/tools/create-stack-user.sh
+        sudo apt-get install git
+        git clone https://opendev.org/openstack/devstack.git
+        sudo ./devstack/tools/create-stack-user.sh
 
    Now you have a stack user that is used to run the DevStack processes. You
-   may want to give your stack user a password to allow SSH via a password::
+   may want to give your stack user a password to allow SSH via a password
 
-       sudo passwd stack
+   .. code-block:: bash
 
-#. Switch to the stack user and clone the DevStack repo again::
+        sudo passwd stack
 
-       sudo su stack
+#. Switch to the stack user and clone the DevStack repo again
-       cd ~
+
-       git clone https://opendev.org/openstack/devstack.git
+   .. code-block:: bash
+
+        sudo su stack
+        cd ~
+        git clone https://opendev.org/openstack/devstack.git
 
 #. For each compute node, copy the provided `local.conf.compute`_ example file
    to the compute node's system at ~/devstack/local.conf. Make sure the
@@ -111,24 +117,30 @@ Detailed DevStack Instructions
    the HOST_IP value is changed appropriately - i.e., HOST_IP is set to the IP
    address of the controller node.
 
-   Note: if you want to use another Watcher git repository (such as a local
+   .. NOTE::
-   one), then change the enable plugin line::
+        if you want to use another Watcher git repository (such as a local
+        one), then change the enable plugin line
+
+   .. code-block:: bash
+
+        enable_plugin watcher <your_local_git_repo> [optional_branch]
 
-       enable_plugin watcher <your_local_git_repo> [optional_branch]
 
    If you do this, then the Watcher DevStack plugin will try to pull the
-   python-watcherclient repo from <your_local_git_repo>/../, so either make
+   python-watcherclient repo from ``<your_local_git_repo>/../``, so either make
-   sure that is also available or specify WATCHERCLIENT_REPO in the local.conf
+   sure that is also available or specify WATCHERCLIENT_REPO in the ``local.conf``
    file.
 
-   Note: if you want to use a specific branch, specify WATCHER_BRANCH in the
+   .. NOTE::
-   local.conf file. By default it will use the master branch.
+        if you want to use a specific branch, specify WATCHER_BRANCH in the
+        local.conf file. By default it will use the master branch.
 
-   Note: watcher-api will default run under apache/httpd, set the variable
+   .. Note::
-   WATCHER_USE_MOD_WSGI=FALSE if you do not wish to run under apache/httpd.
+        watcher-api will default run under apache/httpd, set the variable
-   For development environment it is suggested to set WATHCER_USE_MOD_WSGI
+        WATCHER_USE_MOD_WSGI=FALSE if you do not wish to run under apache/httpd.
-   to FALSE. For Production environment it is suggested to keep it at the
+        For development environment it is suggested to set WATHCER_USE_MOD_WSGI
-   default TRUE value.
+        to FALSE. For Production environment it is suggested to keep it at the
+        default TRUE value.
 
 #. Start stacking from the controller node::
 
@@ -136,8 +148,9 @@ Detailed DevStack Instructions
 
 #. Start stacking on each of the compute nodes using the same command.
 
-#. Configure the environment for live migration via NFS. See the
+   .. seealso::
-   `Multi-Node DevStack Environment`_ section for more details.
+        Configure the environment for live migration via NFS. See the
+        `Multi-Node DevStack Environment`_ section for more details.
 
 .. _local.conf.controller: https://github.com/openstack/watcher/tree/master/devstack/local.conf.controller
 .. _local.conf.compute: https://github.com/openstack/watcher/tree/master/devstack/local.conf.compute
@@ -149,60 +162,19 @@ Since deploying Watcher with only a single compute node is not very useful, a
 few tips are given here for enabling a multi-node environment with live
 migration.
 
-Configuring NFS Server
+.. NOTE::
-----------------------
 
-If you would like to use live migration for shared storage, then the controller
+    Nova supports live migration with local block storage so by default NFS
-can serve as the NFS server if needed::
+    is not required and is considered an advance configuration.
+    The minimum requirements for live migration are:
 
-    sudo apt-get install nfs-kernel-server
+        - all hostnames are resolvable on each host
-    sudo mkdir -p /nfs/instances
+        - all hosts have a passwordless ssh key that is trusted by the other hosts
-    sudo chown stack:stack /nfs/instances
+        - all hosts have a known_hosts file that lists each hosts
 
-Add an entry to `/etc/exports` with the appropriate gateway and netmask
+    If these requirements are met live migration will be possible.
-information::
+    Shared storage such as ceph, booting form cinder volume or nfs are recommend
-
+    when testing evacuate if you want to preserve vm data.
-    /nfs/instances <gateway>/<netmask>(rw,fsid=0,insecure,no_subtree_check,async,no_root_squash)
-
-Export the NFS directories::
-
-    sudo exportfs -ra
-
-Make sure the NFS server is running::
-
-    sudo service nfs-kernel-server status
-
-If the server is not running, then start it::
-
-    sudo service nfs-kernel-server start
-
-Configuring NFS on Compute Node
--------------------------------
-
-Each compute node needs to use the NFS server to hold the instance data::
-
-    sudo apt-get install rpcbind nfs-common
-    mkdir -p /opt/stack/data/instances
-    sudo mount <nfs-server-ip>:/nfs/instances /opt/stack/data/instances
-
-If you would like to have the NFS directory automatically mounted on reboot,
-then add the following to `/etc/fstab`::
-
-    <nfs-server-ip>:/nfs/instances /opt/stack/data/instances nfs auto 0 0
-
-Edit `/etc/libvirt/libvirtd.conf` to make sure the following values are set::
-
-    listen_tls = 0
-    listen_tcp = 1
-    auth_tcp = "none"
-
-Edit `/etc/default/libvirt-bin`::
-
-    libvirtd_opts="-d -l"
-
-Restart the libvirt service::
-
-    sudo service libvirt-bin restart
 
 Setting up SSH keys between compute nodes to enable live migration
 ------------------------------------------------------------------
@@ -231,22 +203,91 @@ must exist in every other compute node's stack user's authorized_keys file and
 every compute node's public ECDSA key needs to be in every other compute
 node's root user's known_hosts file.
 
-Disable serial console
+Configuring NFS Server (ADVANCED)
-----------------------
+---------------------------------
 
-Serial console needs to be disabled for live migration to work.
+If you would like to use live migration for shared storage, then the controller
+can serve as the NFS server if needed
 
-On both the controller and compute node, in /etc/nova/nova.conf
+.. code-block:: bash
 
-[serial_console]
+    sudo apt-get install nfs-kernel-server
-enabled = False
+    sudo mkdir -p /nfs/instances
+    sudo chown stack:stack /nfs/instances
 
-Alternatively, in devstack's local.conf:
+Add an entry to ``/etc/exports`` with the appropriate gateway and netmask
+information
 
-[[post-config|$NOVA_CONF]]
-[serial_console]
-#enabled=false
 
+.. code-block:: bash
+
+    /nfs/instances <gateway>/<netmask>(rw,fsid=0,insecure,no_subtree_check,async,no_root_squash)
+
+Export the NFS directories
+
+.. code-block:: bash
+
+    sudo exportfs -ra
+
+Make sure the NFS server is running
+
+.. code-block:: bash
+
+    sudo service nfs-kernel-server status
+
+If the server is not running, then start it
+
+.. code-block:: bash
+
+    sudo service nfs-kernel-server start
+
+Configuring NFS on Compute Node (ADVANCED)
+------------------------------------------
+
+Each compute node needs to use the NFS server to hold the instance data
+
+.. code-block:: bash
+
+    sudo apt-get install rpcbind nfs-common
+    mkdir -p /opt/stack/data/instances
+    sudo mount <nfs-server-ip>:/nfs/instances /opt/stack/data/instances
+
+If you would like to have the NFS directory automatically mounted on reboot,
+then add the following to ``/etc/fstab``
+
+.. code-block:: bash
+
+    <nfs-server-ip>:/nfs/instances /opt/stack/data/instances nfs auto 0 0
+
+Configuring libvirt to listen on tcp (ADVANCED)
+-----------------------------------------------
+
+.. NOTE::
+
+    By default nova will use ssh as a transport for live migration
+    if you have a low bandwidth connection you can use tcp instead
+    however this is generally not recommended.
+
+
+Edit ``/etc/libvirt/libvirtd.conf`` to make sure the following values are set
+
+.. code-block:: ini
+
+    listen_tls = 0
+    listen_tcp = 1
+    auth_tcp = "none"
+
+Edit ``/etc/default/libvirt-bin``
+
+.. code-block:: ini
+
+    libvirtd_opts="-d -l"
+
+Restart the libvirt service
+
+.. code-block:: bash
+
+    sudo service libvirt-bin restart
 
 VNC server configuration
 ------------------------
@@ -254,13 +295,18 @@ VNC server configuration
 The VNC server listening parameter needs to be set to any address so
 that the server can accept connections from all of the compute nodes.
 
-On both the controller and compute node, in /etc/nova/nova.conf
+On both the controller and compute node, in ``/etc/nova/nova.conf``
 
-vncserver_listen = 0.0.0.0
+.. code-block:: ini
 
-Alternatively, in devstack's local.conf:
+    [vnc]
+    server_listen = "0.0.0.0"
 
-VNCSERVER_LISTEN=0.0.0.0
+Alternatively, in devstack's ``local.conf``:
+
+.. code-block:: bash
+
+    VNCSERVER_LISTEN="0.0.0.0"
 
 
 Environment final checkup

doc/source/contributor/environment.rst

@@ -43,7 +43,7 @@ different version of the above, please document your configuration here!
 Getting the latest code
 =======================
 
-Make a clone of the code from our `Git repository`:
+Make a clone of the code from our ``Git repository``:
 
 .. code-block:: bash
 
@@ -72,9 +72,9 @@ These dependencies can be installed from PyPi_ using the Python tool pip_.
 .. _PyPi: https://pypi.org/
 .. _pip: https://pypi.org/project/pip
 
-However, your system *may* need additional dependencies that `pip` (and by
+However, your system *may* need additional dependencies that ``pip`` (and by
 extension, PyPi) cannot satisfy. These dependencies should be installed
-prior to using `pip`, and the installation method may vary depending on
+prior to using ``pip``, and the installation method may vary depending on
 your platform.
 
 * Ubuntu 16.04::
@@ -141,7 +141,7 @@ forget to activate it:
 
     $ workon watcher
 
-You should then be able to `import watcher` using Python without issue:
+You should then be able to ``import watcher`` using Python without issue:
 
 .. code-block:: bash
 

doc/source/contributor/plugin/strategy-plugin.rst

@@ -300,6 +300,6 @@ Using that you can now query the values for that specific metric:
 .. code-block:: py
 
     avg_meter = self.datasource_backend.statistic_aggregation(
-        instance.uuid, 'cpu_util', self.periods['instance'],
+        instance.uuid, 'instance_cpu_usage', self.periods['instance'],
         self.granularity,
         aggregation=self.aggregation_method['instance'])

doc/source/datasources/grafana.rst

@@ -90,15 +90,15 @@ parameter will need to specify the type of http protocol and the use of
 plain text http is strongly discouraged due to the transmission of the access
 token. Additionally the path to the proxy interface needs to be supplied as
 well in case Grafana is placed in a sub directory of the web server. An example
-would be: `https://mygrafana.org/api/datasource/proxy/` were
+would be: ``https://mygrafana.org/api/datasource/proxy/`` were
-`/api/datasource/proxy` is the default path without any subdirectories.
+``/api/datasource/proxy`` is the default path without any subdirectories.
 Likewise, this parameter can not be placed in the yaml.
 
 To prevent many errors from occurring and potentially filing the logs files it
 is advised to specify the desired datasource in the configuration as it would
 prevent the datasource manager from having to iterate and try possible
-datasources with the launch of each audit. To do this specify `datasources` in
+datasources with the launch of each audit. To do this specify
-the `[watcher_datasources]` group.
+``datasources`` in the ``[watcher_datasources]`` group.
 
 The current configuration that is required to be placed in the traditional
 configuration file would look like the following:
@@ -120,7 +120,7 @@ traditional configuration file or in the yaml, however, it is not advised to
 mix and match but in the case it does occur the yaml would override the
 settings from the traditional configuration file. All five of these parameters
 are dictionaries mapping specific metrics to a configuration parameter. For
-instance the `project_id_map` will specify the specific project id in Grafana
+instance the ``project_id_map`` will specify the specific project id in Grafana
 to be used. The parameters are named as follow:
 
 * project_id_map
@@ -149,10 +149,10 @@ project_id
 
 The project id's can only be determined by someone with the admin role in
 Grafana as that role is required to open the list of projects. The list of
-projects can be found on `/datasources` in the web interface but
+projects can be found on ``/datasources`` in the web interface but
 unfortunately it does not immediately display the project id. To display
 the id one can best hover the mouse over the projects and the url will show the
-project id's for example `/datasources/edit/7563`. Alternatively the entire
+project id's for example ``/datasources/edit/7563``. Alternatively the entire
 list of projects can be retrieved using the `REST api`_. To easily make
 requests to the REST api a tool such as Postman can be used.
 
@@ -239,18 +239,24 @@ conversion from bytes to megabytes.
 
     SELECT value/1000000 FROM memory...
 
-Queries will be formatted using the .format string method within Python. This
+Queries will be formatted using the .format string method within Python.
-format will currently have give attributes exposed to it labeled `{0}` to
+This format will currently have give attributes exposed to it labeled
-`{4}`. Every occurrence of these characters within the string will be replaced
+``{0}`` through ``{4}``.
+Every occurrence of these characters within the string will be replaced
 with the specific attribute.
 
-- {0} is the aggregate typically `mean`, `min`, `max` but `count` is also
+{0}
-  supported.
+    is the aggregate typically ``mean``, ``min``, ``max`` but ``count``
-- {1} is the attribute as specified in the attribute parameter.
+    is also supported.
-- {2} is the period of time to aggregate data over in seconds.
+{1}
-- {3} is the granularity or the interval between data points in seconds.
+    is the attribute as specified in the attribute parameter.
-- {4} is translator specific and in the case of InfluxDB it will be used for
+{2}
-  retention_periods.
+    is the period of time to aggregate data over in seconds.
+{3}
+    is the granularity or the interval between data points in seconds.
+{4}
+    is translator specific and in the case of InfluxDB it will be used for
+    retention_periods.
 
 **InfluxDB**
 

doc/source/datasources/prometheus.rst

@@ -0,0 +1,140 @@
+=====================
+Prometheus datasource
+=====================
+
+Synopsis
+--------
+The Prometheus datasource allows Watcher to use a Prometheus server as the
+source for collected metrics used by the Watcher decision engine. At minimum
+deployers must configure the ``host`` and ``port`` at which the Prometheus
+server is listening.
+
+Requirements
+-------------
+It is required that Prometheus metrics contain a label to identify the hostname
+of the exporter from which the metric was collected. This is used to match
+against the Watcher cluster model ``ComputeNode.hostname``. The default for
+this label is ``fqdn`` and in the prometheus scrape configs would look like:
+
+.. code-block::
+
+    scrape_configs:
+    - job_name: node
+      static_configs:
+     - targets: ['10.1.2.3:9100']
+        labels:
+          fqdn: "testbox.controlplane.domain"
+
+This default can be overridden when a deployer uses a different label to
+identify the exporter host (for example ``hostname`` or ``host``, or any other
+label, as long as it identifies the host).
+
+Internally this label is used in creating a ``fqdn_instance_map``, mapping
+the fqdn with the Prometheus instance label associated with each exporter.
+The keys of the resulting fqdn_instance_map are expected to match the
+``ComputeNode.hostname`` used in the Watcher decision engine cluster model.
+An example ``fqdn_instance_map`` is the following:
+
+.. code-block::
+
+    {
+     'ena.controlplane.domain': '10.1.2.1:9100',
+     'dio.controlplane.domain': '10.1.2.2:9100',
+     'tria.controlplane.domain': '10.1.2.3:9100'
+    }
+
+For instance metrics, it is required that Prometheus contains a label
+with the uuid of the OpenStack instance in each relevant metric. By default,
+the datasource will look for the label ``resource``. The
+``instance_uuid_label`` config option in watcher.conf allows deployers to
+override this default to any other label name that stores the  ``uuid``.
+
+Limitations
+-----------
+The current implementation doesn't support the ``statistic_series`` function of
+the Watcher ``class DataSourceBase``. It is expected that the
+``statistic_aggregation`` function (which is implemented) is sufficient in
+providing the **current** state of the managed resources in the cluster.
+The ``statistic_aggregation`` function defaults to querying back 300 seconds,
+starting from the present time (the time period is a function parameter and
+can be set to a value as required). Implementing the ``statistic_series`` can
+always be re-visited if the requisite interest and work cycles are volunteered
+by the interested parties.
+
+One further note about a limitation in the implemented
+``statistic_aggregation`` function. This function is defined with a
+``granularity`` parameter, to be used when querying whichever of the Watcher
+``DataSourceBase`` metrics providers. In the case of Prometheus, we do not
+fetch and then process individual metrics across the specified time period.
+Instead we use the PromQL querying operators and functions, so that the
+server itself will process the request across the specified parameters and
+then return the result. So ``granularity`` parameter is redundant and remains
+unused for the Prometheus implementation of ``statistic_aggregation``. The
+granularity of the data fetched by Prometheus server is specified in
+configuration as the server ``scrape_interval`` (current default 15 seconds).
+
+Configuration
+-------------
+A deployer must set the ``datasources`` parameter to include ``prometheus``
+under the watcher_datasources section of watcher.conf (or add ``prometheus`` in
+datasources for a specific strategy if preferred eg. under the
+``[watcher_strategies.workload_stabilization]`` section).
+
+The watcher.conf configuration file is also used to set the parameter values
+required by the Watcher Prometheus data source. The configuration can be
+added under the ``[prometheus_client]`` section and the available options are
+duplicated below from the code as they are self documenting:
+
+.. code-block::
+
+    cfg.StrOpt('host',
+               help="The hostname or IP address for the prometheus server."),
+    cfg.StrOpt('port',
+               help="The port number used by the prometheus server."),
+    cfg.StrOpt('fqdn_label',
+               default="fqdn",
+               help="The label that Prometheus uses to store the fqdn of "
+                    "exporters. Defaults to 'fqdn'."),
+    cfg.StrOpt('instance_uuid_label',
+               default="resource",
+               help="The label that Prometheus uses to store the uuid of "
+                    "OpenStack instances. Defaults to 'resource'."),
+    cfg.StrOpt('username',
+               help="The basic_auth username to use to authenticate with the "
+                    "Prometheus server."),
+    cfg.StrOpt('password',
+               secret=True,
+               help="The basic_auth password to use to authenticate with the "
+                    "Prometheus server."),
+    cfg.StrOpt('cafile',
+               help="Path to the CA certificate for establishing a TLS "
+                    "connection with the Prometheus server."),
+    cfg.StrOpt('certfile',
+               help="Path to the client certificate for establishing a TLS "
+                    "connection with the Prometheus server."),
+    cfg.StrOpt('keyfile',
+               help="Path to the client key for establishing a TLS "
+                    "connection with the Prometheus server."),
+
+The ``host`` and ``port`` are **required** configuration options which have
+no set default. These specify the hostname (or IP) and port for at which
+the Prometheus server is listening. The ``fqdn_label`` allows deployers to
+override the required metric label used to match Prometheus node exporters
+against the Watcher ComputeNodes in the Watcher decision engine cluster data
+model. The default is ``fqdn`` and deployers can specify any other value
+(e.g. if they have an equivalent but different label such as ``host``).
+
+So a sample watcher.conf configured to use the Prometheus server at
+``10.2.3.4:9090`` would look like the following:
+
+.. code-block::
+
+    [watcher_datasources]
+
+    datasources = prometheus
+
+    [prometheus_client]
+
+    host = 10.2.3.4
+    port = 9090
+    fqdn_label = fqdn

doc/source/install/common_configure.rst

@@ -9,7 +9,7 @@
         ...
         connection = mysql+pymysql://watcher:WATCHER_DBPASS@controller/watcher?charset=utf8
 
-   * In the `[DEFAULT]` section, configure the transport url for RabbitMQ message broker.
+   * In the ``[DEFAULT]`` section, configure the transport url for RabbitMQ message broker.
 
      .. code-block:: ini
 
@@ -20,7 +20,7 @@
 
      Replace the RABBIT_PASS with the password you chose for OpenStack user in RabbitMQ.
 
-   * In the `[keystone_authtoken]` section, configure Identity service access.
+   * In the ``[keystone_authtoken]`` section, configure Identity service access.
 
      .. code-block:: ini
 
@@ -39,7 +39,7 @@
      Replace WATCHER_PASS with the password you chose for the watcher user in the Identity service.
 
    * Watcher interacts with other OpenStack projects via project clients, in order to instantiate these
-     clients, Watcher requests new session from Identity service. In the `[watcher_clients_auth]` section,
+     clients, Watcher requests new session from Identity service. In the ``[watcher_clients_auth]`` section,
      configure the identity service access to interact with other OpenStack project clients.
 
      .. code-block:: ini
@@ -56,7 +56,7 @@
 
      Replace WATCHER_PASS with the password you chose for the watcher user in the Identity service.
 
-   * In the `[api]` section, configure host option.
+   * In the ``[api]`` section, configure host option.
 
      .. code-block:: ini
 
@@ -66,7 +66,7 @@
 
      Replace controller with the IP address of the management network interface on your controller node, typically 10.0.0.11 for the first node in the example architecture.
 
-   * In the `[oslo_messaging_notifications]` section, configure the messaging driver.
+   * In the ``[oslo_messaging_notifications]`` section, configure the messaging driver.
 
      .. code-block:: ini
 

doc/source/man/general-options.rst

@@ -48,7 +48,7 @@
         logging configuration to any other existing logging
         options. Please see the Python logging module documentation
         for details on logging configuration files. The log-config
-        name for this option is depcrecated.
+        name for this option is deprecated.
 
   **--log-format FORMAT**
         A logging.Formatter log message format string which may use any

doc/source/strategies/basic-server-consolidation.rst

@@ -26,8 +26,7 @@ metric                       service name plugins comment
                                                   ``compute_monitors`` option
                                                   to ``cpu.virt_driver`` in
                                                   the nova.conf.
-``cpu_util``                 ceilometer_  none    cpu_util has been removed
+``cpu``                      ceilometer_  none
-                                                  since Stein.
 ============================ ============ ======= ===========================
 
 .. _ceilometer: https://docs.openstack.org/ceilometer/latest/admin/telemetry-measurements.html#openstack-compute

doc/source/strategies/vm_workload_consolidation.rst

@@ -22,14 +22,19 @@ The *vm_workload_consolidation* strategy requires the following metrics:
 ============================ ============ ======= =========================
 metric                       service name plugins comment
 ============================ ============ ======= =========================
-``cpu_util``                 ceilometer_  none    cpu_util has been removed
+``cpu``                      ceilometer_  none
-                                                  since Stein.
 ``memory.resident``          ceilometer_  none
 ``memory``                   ceilometer_  none
 ``disk.root.size``           ceilometer_  none
+``compute.node.cpu.percent`` ceilometer_  none    (optional) need to set the
+                                                  ``compute_monitors`` option
+                                                  to ``cpu.virt_driver`` in the
+                                                  nova.conf.
+``hardware.memory.used``     ceilometer_  SNMP_   (optional)
 ============================ ============ ======= =========================
 
 .. _ceilometer: https://docs.openstack.org/ceilometer/latest/admin/telemetry-measurements.html#openstack-compute
+.. _SNMP: https://docs.openstack.org/ceilometer/latest/admin/telemetry-measurements.html#snmp-based-meters
 
 Cluster data model
 ******************

doc/source/strategies/workload-stabilization.rst

@@ -27,9 +27,8 @@ metric                       service name plugins comment
                                                   to ``cpu.virt_driver`` in the
                                                   nova.conf.
 ``hardware.memory.used``     ceilometer_  SNMP_
-``cpu_util``                 ceilometer_  none    cpu_util has been removed
+``cpu``                      ceilometer_  none
-                                                  since Stein.
+``instance_ram_usage``       ceilometer_  none
-``memory.resident``          ceilometer_  none
 ============================ ============ ======= =============================
 
 .. _ceilometer: https://docs.openstack.org/ceilometer/latest/admin/telemetry-measurements.html#openstack-compute
@@ -107,10 +106,10 @@ parameter            type   default Value         description
                                                   period of all received ones.
 ==================== ====== ===================== =============================
 
-.. |metrics| replace:: ["cpu_util", "memory.resident"]
+.. |metrics| replace:: ["instance_cpu_usage", "instance_ram_usage"]
-.. |thresholds| replace:: {"cpu_util": 0.2, "memory.resident": 0.2}
+.. |thresholds| replace:: {"instance_cpu_usage": 0.2, "instance_ram_usage": 0.2}
-.. |weights| replace:: {"cpu_util_weight": 1.0, "memory.resident_weight": 1.0}
+.. |weights| replace:: {"instance_cpu_usage_weight": 1.0, "instance_ram_usage_weight": 1.0}
-.. |instance_metrics| replace:: {"cpu_util": "compute.node.cpu.percent", "memory.resident": "hardware.memory.used"}
+.. |instance_metrics| replace:: {"instance_cpu_usage": "compute.node.cpu.percent", "instance_ram_usage": "hardware.memory.used"}
 .. |periods| replace:: {"instance": 720, "node": 600}
 
 Efficacy Indicator
@@ -136,8 +135,8 @@ How to use it ?
       at1 workload_balancing --strategy workload_stabilization
 
     $ openstack optimize audit create -a at1 \
-      -p thresholds='{"memory.resident": 0.05}' \
+      -p thresholds='{"instance_ram_usage": 0.05}' \
-      -p metrics='["memory.resident"]'
+      -p metrics='["instance_ram_usage"]'
 
 External Links
 --------------

doc/source/strategies/workload_balance.rst

@@ -24,8 +24,7 @@ The *workload_balance* strategy requires the following metrics:
 ======================= ============ ======= =========================
 metric                  service name plugins comment
 ======================= ============ ======= =========================
-``cpu_util``            ceilometer_  none    cpu_util has been removed
+``cpu``                 ceilometer_  none
-                                             since Stein.
 ``memory.resident``     ceilometer_  none
 ======================= ============ ======= =========================
 
@@ -65,15 +64,16 @@ Configuration
 
 Strategy parameters are:
 
-============== ====== ============= ====================================
+============== ====== ==================== ====================================
-parameter      type   default Value description
+parameter      type   default Value        description
-============== ====== ============= ====================================
+============== ====== ==================== ====================================
-``metrics``    String 'cpu_util'    Workload balance base on cpu or ram
+``metrics``    String 'instance_cpu_usage' Workload balance base on cpu or ram
-                                    utilization. choice: ['cpu_util',
+                                           utilization. Choices:
-                                    'memory.resident']
+                                           ['instance_cpu_usage',
-``threshold``  Number 25.0          Workload threshold for migration
+                                           'instance_ram_usage']
-``period``     Number 300           Aggregate time period of ceilometer
+``threshold``  Number 25.0                 Workload threshold for migration
-============== ====== ============= ====================================
+``period``     Number 300                  Aggregate time period of ceilometer
+============== ====== ==================== ====================================
 
 Efficacy Indicator
 ------------------
@@ -95,7 +95,7 @@ How to use it ?
       at1 workload_balancing --strategy workload_balance
 
     $ openstack optimize audit create -a at1 -p threshold=26.0 \
-            -p period=310 -p metrics=cpu_util
+            -p period=310 -p metrics=instance_cpu_usage
 
 External Links
 --------------

doc/source/user/user-guide.rst

@@ -132,8 +132,8 @@ audit) that you want to use.
   $ openstack optimize audit create -a <your_audit_template>
 
 If your_audit_template was created by --strategy <your_strategy>, and it
-defines some parameters (command `watcher strategy show` to check parameters
+defines some parameters (command ``watcher strategy show`` to check parameters
-format), your can append `-p` to input required parameters:
+format), your can append ``-p`` to input required parameters:
 
 .. code:: bash
 

playbooks/generate_prometheus_config.yml

@@ -0,0 +1,9 @@
+---
+- hosts: all
+  tasks:
+    - name: Generate prometheus.yml config file
+      delegate_to: controller
+      template:
+        src: "templates/prometheus.yml.j2"
+        dest: "/home/zuul/prometheus.yml"
+        mode: "0644"

playbooks/templates/prometheus.yml.j2

@@ -0,0 +1,13 @@
+global:
+  scrape_interval: 10s
+scrape_configs:
+  - job_name: "node"
+    static_configs:
+      - targets: ["localhost:3000"]
+{% if 'compute' in groups %}
+{% for host in groups['compute'] %}
+      - targets: ["{{ hostvars[host]['ansible_fqdn'] }}:9100"]
+        labels:
+          fqdn: "{{ hostvars[host]['ansible_fqdn'] }}"
+{% endfor %}
+{% endif %}

rally-jobs/README.rst

@@ -1,7 +1,8 @@
 Rally job
 =========
 
-We provide, with Watcher, a Rally plugin you can use to benchmark the optimization service.
+We provide, with Watcher, a Rally plugin you can use to benchmark
+the optimization service.
 
 To launch this task with configured Rally you just need to run:
 

releasenotes/notes/2025.1-prelude-8be97eece4e1d1ff.yaml

@@ -0,0 +1,33 @@
+---
+prelude: |
+  The ``Openstack 2025.1`` (``Watcher 14.0.0``) includes several new features,
+  deprecations, and removals. After a period of inactivity, the Watcher
+  project moved to the Distributed leadership model in ``2025.1`` with
+  several new contributors working to modernize the code base.
+  Activity this cycle was mainly focused on paying down technical debt
+  related to supporting newer testing runtimes. With this release,
+  ``ubuntu 24.04`` is now officially tested and supported.
+
+  ``Ubuntu 24.04`` brings a new default Python runtime ``3.12`` and with it
+  improvements to eventlet and SQLAlchemy 2.0 compatibility where required.
+  ``2025.1`` is the last release to officially support and test with ``Ubuntu 22.04``.
+
+  ``2025.1`` is the second official skip-level upgrade release supporting
+  upgrades from either ``2024.1`` or ``2024.2``
+
+  Another area of focus in this cycle was the data sources supported by Watcher.
+  The long obsolete `Ceilometer` API data source has been removed, and the untested
+  `Monasca` data source has been deprecated and a new `Prometheus` data source
+  has been added.
+  https://specs.openstack.org/openstack/watcher-specs/specs/2025.1/approved/prometheus-datasource.html
+fixes:
+  - https://bugs.launchpad.net/watcher/+bug/2086710 watcher compatibility between
+    eventlet, apscheduler, and python 3.12
+  - https://bugs.launchpad.net/watcher/+bug/2067815 refactoring of the SQLAlchemy
+    database layer to improve compatibility with eventlet on newer Pythons
+  - A number of linting issues were addressed with the introduction
+    of pre-commit. The issues include but are not limited to, spelling and grammar
+    fixes across all documentation and code, numerous sphinx documentation build warnings
+    , and incorrect file permission such as files having the execute bit set when not required.
+    While none of these changes should affect the runtime behavior of Watcher, they
+    generally improve the maintainability and quality of the codebase.

releasenotes/notes/add-instance-metrics-to-prometheus-datasource-9fba8c174ff845e1.yaml

@@ -0,0 +1,6 @@
+---
+features:
+  - |
+    Support for instance metrics has been added to the prometheus data source.
+    The included metrics are `instance_cpu_usage`, `instance_ram_usage`,
+    `instance_ram_allocated` and `instance_root_disk_size`.

releasenotes/notes/add-scoring-module-fa00d013ed2d614e.yaml

@@ -4,4 +4,4 @@ features:
     will standardize interactions with scoring engines
     through the common API. It is possible to use the
     scoring engine by different Strategies, which
-    improve the code and data model re-use.
+    improve the code and data model reuse.

releasenotes/notes/api-call-retry-fef741ac684c58dd.yaml

@@ -5,5 +5,5 @@ features:
     failure. The amount of failures allowed before giving up and the time before
     reattempting are configurable. The `api_call_retries` and
     `api_query_timeout` parameters in the `[collector]` group can be used to
-    adjust these paremeters. 10 retries with a 1 second time in between
+    adjust these parameters. 10 retries with a 1 second time in between
     reattempts is the default.

releasenotes/notes/api-microversioning-7999a3ee8073bf32.yaml

@@ -3,6 +3,6 @@ features:
     Watcher starts to support API microversions since Stein cycle. From now
     onwards all API changes should be made with saving backward compatibility.
     To specify API version operator should use OpenStack-API-Version
-    HTTP header. If operator wants to know the mininum and maximum supported
+    HTTP header. If operator wants to know the minimum and maximum supported
     versions by API, he/she can access /v1 resource and Watcher API will
     return appropriate headers in response.

releasenotes/notes/deprecate-monasca-ds-9065f4d4bee09ab2.yaml

@@ -0,0 +1,5 @@
+---
+deprecations:
+  - |
+    Monasca Data Source is deprecated and will be removed in the future, due
+    to inactivity of Monasca project.

releasenotes/notes/drop-python38-support-eeb19a0bc0160sw1.yaml

@@ -0,0 +1,6 @@
+---
+upgrade:
+  - |
+    Python 3.8 support has been dropped. Last release of watcher
+    supporting python 3.8 is 13.0.0.
+    The minimum version of Python now supported is Python 3.9.

releasenotes/notes/general-purpose-decision-engine-threadpool-0711b23abfc9d409.yaml

@@ -7,7 +7,7 @@ prelude: >
 features:
   - |
     A new threadpool for the decision engine that contributors can use to
-    improve the performance of many operations, primarily I/O bound onces.
+    improve the performance of many operations, primarily I/O bound ones.
     The amount of workers used by the decision engine threadpool can be
     configured to scale according to the available infrastructure using
     the `watcher_decision_engine.max_general_workers` config option.

releasenotes/notes/improve-compute-data-model-b427c85e4ed2b6fb.yaml

@@ -13,7 +13,7 @@ features:
     * disk_gb_reserved: The amount of disk a node has reserved for its own use.
     * disk_ratio: Disk allocation ratio.
 
-    We also add some new propeties:
+    We also add some new properties:
 
     * vcpu_capacity: The amount of vcpu, take allocation ratio into account,
       but do not include reserved.

releasenotes/notes/prometheus-datasource-e56f2f7b8f3427c2.yaml

@@ -0,0 +1,8 @@
+---
+features:
+  - |
+    A new Prometheus data source is added. This allows the watcher decision
+    engine to collect metrics from Prometheus server. For more information
+    about the Prometheus data source, including limitations and configuration
+    options see
+    https://docs.openstack.org/watcher/latest/datasources/prometheus.html

releasenotes/notes/remove-ceilometer-datasource-8d9ab7d64d61e405.yaml

@@ -0,0 +1,6 @@
+---
+upgrade:
+  - |
+    Ceilometer datasource has been completely removed. The datasource requires
+    ceilometer API which was already removed from Ceilometer. Use the other
+    datasources such as Gnocchi.

releasenotes/notes/stale-action-plan-b6a6b08df873c128.yaml

@@ -1,4 +1,4 @@
 ---
 features:
-  - Check the creation time of the action plan, 
+  - Check the creation time of the action plan,
     and set its state to SUPERSEDED if it has expired.

releasenotes/notes/watcher-notifications-ovo-7b44d52ef6400dd0.yaml

@@ -4,5 +4,5 @@ features:
     Whenever a Watcher object is created, updated or deleted, a versioned
     notification will, if it's relevant, be automatically sent to notify in order
     to allow an event-driven style of architecture within Watcher. Moreover, it
-    will also give other services and/or 3rd party softwares (e.g. monitoring
+    will also give other services and/or 3rd party software (e.g. monitoring
     solutions or rules engines) the ability to react to such events.

releasenotes/notes/watcher-service-list-7b2f4b64f71e9b89.yaml

@@ -1,3 +1,3 @@
 ---
 features:
-  - Add a service supervisor to watch Watcher deamons.
+  - Add a service supervisor to watch Watcher daemons.

releasenotes/source/2023.1.rst

@@ -0,0 +1,6 @@
+===========================
+2023.1 Series Release Notes
+===========================
+
+.. release-notes::
+   :branch: unmaintained/2023.1

releasenotes/source/2023.2.rst

@@ -0,0 +1,6 @@
+===========================
+2023.2 Series Release Notes
+===========================
+
+.. release-notes::
+   :branch: stable/2023.2

releasenotes/source/2024.1.rst

@@ -0,0 +1,6 @@
+===========================
+2024.1 Series Release Notes
+===========================
+
+.. release-notes::
+   :branch: stable/2024.1

releasenotes/source/2024.2.rst

@@ -0,0 +1,6 @@
+===========================
+2024.2 Series Release Notes
+===========================
+
+.. release-notes::
+   :branch: stable/2024.2

releasenotes/source/conf.py

@@ -28,12 +28,12 @@ import sys
 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
-#sys.path.insert(0, os.path.abspath('.'))
+# sys.path.insert(0, os.path.abspath('.'))
 
 # -- General configuration ----------------------------------------------------
 
 # If your documentation needs a minimal Sphinx version, state it here.
-#needs_sphinx = '1.0'
+# needs_sphinx = '1.0'
 
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
@@ -47,7 +47,7 @@ templates_path = ['_templates']
 source_suffix = '.rst'
 
 # The encoding of source files.
-#source_encoding = 'utf-8-sig'
+# source_encoding = 'utf-8-sig'
 
 # The master toctree document.
 master_doc = 'index'
@@ -63,37 +63,37 @@ release = ''
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
-#language = None
+# language = None
 
 # There are two options for replacing |today|: either, you set today to some
 # non-false value, then it is used:
-#today = ''
+# today = ''
 # Else, today_fmt is used as the format for a strftime call.
-#today_fmt = '%B %d, %Y'
+# today_fmt = '%B %d, %Y'
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
 exclude_patterns = ['_build']
 
 # The reST default role (used for this markup: `text`) to use for all documents
-#default_role = None
+# default_role = None
 
 # If true, '()' will be appended to :func: etc. cross-reference text.
-#add_function_parentheses = True
+# add_function_parentheses = True
 
 # If true, the current module name will be prepended to all description
 # unit titles (such as .. function::).
-#add_module_names = True
+# add_module_names = True
 
 # If true, sectionauthor and moduleauthor directives will be shown in the
 # output. They are ignored by default.
-#show_authors = False
+# show_authors = False
 
 # The name of the Pygments (syntax highlighting) style to use.
 pygments_style = 'native'
 
 # A list of ignored prefixes for module index sorting.
-#modindex_common_prefix = []
+# modindex_common_prefix = []
 
 # openstackdocstheme options
 openstackdocs_repo_name = 'openstack/watcher'
@@ -109,26 +109,26 @@ html_theme = 'openstackdocs'
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
 # documentation.
-#html_theme_options = {}
+# html_theme_options = {}
 
 # Add any paths that contain custom themes here, relative to this directory.
-#html_theme_path = []
+# html_theme_path = []
 
 # The name for this set of Sphinx documents.  If None, it defaults to
 # "<project> v<release> documentation".
-#html_title = None
+# html_title = None
 
 # A shorter title for the navigation bar.  Default is the same as html_title.
-#html_short_title = None
+# html_short_title = None
 
 # The name of an image file (relative to this directory) to place at the top
 # of the sidebar.
-#html_logo = None
+# html_logo = None
 
 # The name of an image file (within the static path) to use as favicon of the
 # docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
 # pixels large.
-#html_favicon = None
+# html_favicon = None
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
@@ -137,44 +137,44 @@ html_static_path = ['_static']
 
 # If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
 # using the given strftime format.
-#html_last_updated_fmt = '%b %d, %Y'
+# html_last_updated_fmt = '%b %d, %Y'
 
 # If true, SmartyPants will be used to convert quotes and dashes to
 # typographically correct entities.
-#html_use_smartypants = True
+# html_use_smartypants = True
 
 # Custom sidebar templates, maps document names to template names.
-#html_sidebars = {}
+# html_sidebars = {}
 
 # Additional templates that should be rendered to pages, maps page names to
 # template names.
-#html_additional_pages = {}
+# html_additional_pages = {}
 
 # If false, no module index is generated.
-#html_domain_indices = True
+# html_domain_indices = True
 
 # If false, no index is generated.
-#html_use_index = True
+# html_use_index = True
 
 # If true, the index is split into individual pages for each letter.
-#html_split_index = False
+# html_split_index = False
 
 # If true, links to the reST sources are added to the pages.
-#html_show_sourcelink = True
+# html_show_sourcelink = True
 
 # If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
-#html_show_sphinx = True
+# html_show_sphinx = True
 
 # If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
-#html_show_copyright = True
+# html_show_copyright = True
 
 # If true, an OpenSearch description file will be output, and all pages will
 # contain a <link> tag referring to it.  The value of this option must be the
 # base URL from which the finished HTML is served.
-#html_use_opensearch = ''
+# html_use_opensearch = ''
 
 # This is the file name suffix for HTML files (e.g. ".xhtml").
-#html_file_suffix = None
+# html_file_suffix = None
 
 # Output file base name for HTML help builder.
 htmlhelp_basename = 'watcherdoc'
@@ -183,42 +183,42 @@ htmlhelp_basename = 'watcherdoc'
 # -- Options for LaTeX output -------------------------------------------------
 
 latex_elements = {
-# The paper size ('letterpaper' or 'a4paper').
+    # The paper size ('letterpaper' or 'a4paper').
-#'papersize': 'letterpaper',
+    # 'papersize': 'letterpaper',
 
-# The font size ('10pt', '11pt' or '12pt').
+    # The font size ('10pt', '11pt' or '12pt').
-#'pointsize': '10pt',
+    # 'pointsize': '10pt',
 
-# Additional stuff for the LaTeX preamble.
+    # Additional stuff for the LaTeX preamble.
-#'preamble': '',
+    # 'preamble': '',
 }
 
 # Grouping the document tree into LaTeX files. List of tuples
 # (source start file, target name, title, author, documentclass [howto/manual])
 latex_documents = [
-  ('index', 'watcher.tex', 'Watcher Documentation',
+    ('index', 'watcher.tex', 'Watcher Documentation',
-   'Watcher developers', 'manual'),
+     'Watcher developers', 'manual'),
 ]
 
 # The name of an image file (relative to this directory) to place at the top of
 # the title page.
-#latex_logo = None
+# latex_logo = None
 
 # For "manual" documents, if this is true, then toplevel headings are parts,
 # not chapters.
-#latex_use_parts = False
+# latex_use_parts = False
 
 # If true, show page references after internal links.
-#latex_show_pagerefs = False
+# latex_show_pagerefs = False
 
 # If true, show URL addresses after external links.
-#latex_show_urls = False
+# latex_show_urls = False
 
 # Documents to append as an appendix to all manuals.
-#latex_appendices = []
+# latex_appendices = []
 
 # If false, no module index is generated.
-#latex_domain_indices = True
+# latex_domain_indices = True
 
 
 # -- Options for manual page output -------------------------------------------
@@ -231,7 +231,7 @@ man_pages = [
 ]
 
 # If true, show URL addresses after external links.
-#man_show_urls = False
+# man_show_urls = False
 
 
 # -- Options for Texinfo output -----------------------------------------------
@@ -240,19 +240,19 @@ man_pages = [
 # (source start file, target name, title, author,
 #  dir menu entry, description, category)
 texinfo_documents = [
-  ('index', 'watcher', 'Watcher Documentation',
+    ('index', 'watcher', 'Watcher Documentation',
-   'Watcher developers', 'watcher', 'One line description of project.',
+     'Watcher developers', 'watcher', 'One line description of project.',
-   'Miscellaneous'),
+     'Miscellaneous'),
 ]
 
 # Documents to append as an appendix to all manuals.
-#texinfo_appendices = []
+# texinfo_appendices = []
 
 # If false, no module index is generated.
-#texinfo_domain_indices = True
+# texinfo_domain_indices = True
 
 # How to display URL addresses: 'footnote', 'no', or 'inline'.
-#texinfo_show_urls = 'footnote'
+# texinfo_show_urls = 'footnote'
 
 # -- Options for Internationalization output ------------------------------
 locale_dirs = ['locale/']

releasenotes/source/index.rst

@@ -21,6 +21,10 @@ Contents:
    :maxdepth: 1
 
    unreleased
+   2024.2
+   2024.1
+   2023.2
+   2023.1
    zed
    yoga
    xena

releasenotes/source/locale/en_GB/LC_MESSAGES/releasenotes.po

@@ -2,15 +2,17 @@
 # Andi Chandler <andi@gowling.com>, 2018. #zanata
 # Andi Chandler <andi@gowling.com>, 2020. #zanata
 # Andi Chandler <andi@gowling.com>, 2022. #zanata
+# Andi Chandler <andi@gowling.com>, 2023. #zanata
+# Andi Chandler <andi@gowling.com>, 2024. #zanata
 msgid ""
 msgstr ""
 "Project-Id-Version: python-watcher\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2022-08-29 03:02+0000\n"
+"POT-Creation-Date: 2025-01-10 00:32+0000\n"
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"PO-Revision-Date: 2022-05-31 08:39+0000\n"
+"PO-Revision-Date: 2024-04-18 12:21+0000\n"
 "Last-Translator: Andi Chandler <andi@gowling.com>\n"
 "Language-Team: English (United Kingdom)\n"
 "Language: en_GB\n"
@@ -59,12 +61,24 @@ msgstr "1.9.0"
 msgid "2.0.0"
 msgstr "2.0.0"
 
+msgid "2023.1 Series Release Notes"
+msgstr "2023.1 Series Release Notes"
+
+msgid "2023.2 Series Release Notes"
+msgstr "2023.2 Series Release Notes"
+
 msgid "3.0.0"
 msgstr "3.0.0"
 
+msgid "3.0.0.0rc1"
+msgstr "3.0.0.0rc1"
+
 msgid "4.0.0"
 msgstr "4.0.0"
 
+msgid "4.0.0.0rc1"
+msgstr "4.0.0.0rc1"
+
 msgid "6.0.0"
 msgstr "6.0.0"
 
@@ -206,6 +220,17 @@ msgstr ""
 msgid "Added SUSPENDED audit state"
 msgstr "Added SUSPENDED audit state"
 
+msgid ""
+"Added a generic scoring engine module, which will standardize interactions "
+"with scoring engines through the common API. It is possible to use the "
+"scoring engine by different Strategies, which improve the code and data "
+"model re-use."
+msgstr ""
+"Added a generic scoring engine module, which will standardize interactions "
+"with scoring engines through the common API. It is possible to use the "
+"scoring engine by different Strategies, which improve the code and data "
+"model re-use."
+
 msgid ""
 "Added a generic scoring engine module, which will standarize interactions "
 "with scoring engines through the common API. It is possible to use the "
@@ -325,6 +350,13 @@ msgstr ""
 "Added a way to create periodic audit to be able to continuously optimise the "
 "cloud infrastructure."
 
+msgid ""
+"Added a way to return the of available goals depending on which strategies "
+"have been deployed on the node where the decision engine is running."
+msgstr ""
+"Added a way to return the of available goals depending on which strategies "
+"have been deployed on the node where the decision engine is running."
+
 msgid ""
 "Added a way to return the of available goals depending on which strategies "
 "have been deployed on the node where the decison engine is running."
@@ -401,6 +433,15 @@ msgstr ""
 "that negatively affects performance of a high priority VM by over utilising "
 "Last Level Cache."
 
+msgid ""
+"Added strategy to identify and migrate a Noisy Neighbor - a low priority VM "
+"that negatively affects performance of a high priority VM by over utilizing "
+"Last Level Cache."
+msgstr ""
+"Added strategy to identify and migrate a Noisy Neighbour - a low-priority VM "
+"that negatively affects the performance of a high-priority VM by over "
+"utilising Last Level Cache."
+
 msgid ""
 "Added the functionality to filter out instances which have metadata field "
 "'optimize' set to False. For now, this is only available for the "
@@ -507,6 +548,13 @@ msgstr ""
 msgid "Centralize all configuration options for Watcher."
 msgstr "Centralise all configuration options for Watcher."
 
+msgid ""
+"Check the creation time of the action plan, and set its state to SUPERSEDED "
+"if it has expired."
+msgstr ""
+"Check the creation time of the action plan, and set its state to SUPERSEDED "
+"if it has expired."
+
 msgid "Contents:"
 msgstr "Contents:"
 
@@ -969,6 +1017,9 @@ msgstr "Xena Series Release Notes"
 msgid "Yoga Series Release Notes"
 msgstr "Yoga Series Release Notes"
 
+msgid "Zed Series Release Notes"
+msgstr "Zed Series Release Notes"
+
 msgid "``[watcher_datasources] datasources = gnocchi,monasca,ceilometer``"
 msgstr "``[watcher_datasources] datasources = gnocchi,monasca,ceilometer``"
 

releasenotes/source/locale/fr/LC_MESSAGES/releasenotes.po

@@ -1,33 +0,0 @@
-# Gérald LONLAS <g.lonlas@gmail.com>, 2016. #zanata
-msgid ""
-msgstr ""
-"Project-Id-Version: python-watcher\n"
-"Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2019-03-22 02:21+0000\n"
-"MIME-Version: 1.0\n"
-"Content-Type: text/plain; charset=UTF-8\n"
-"Content-Transfer-Encoding: 8bit\n"
-"PO-Revision-Date: 2016-10-22 06:44+0000\n"
-"Last-Translator: Gérald LONLAS <g.lonlas@gmail.com>\n"
-"Language-Team: French\n"
-"Language: fr\n"
-"X-Generator: Zanata 4.3.3\n"
-"Plural-Forms: nplurals=2; plural=(n > 1)\n"
-
-msgid "0.29.0"
-msgstr "0.29.0"
-
-msgid "Contents:"
-msgstr "Contenu :"
-
-msgid "Current Series Release Notes"
-msgstr "Note de la release actuelle"
-
-msgid "New Features"
-msgstr "Nouvelles fonctionnalités"
-
-msgid "Newton Series Release Notes"
-msgstr "Note de release pour Newton"
-
-msgid "Welcome to watcher's Release Notes documentation!"
-msgstr "Bienvenue dans la documentation de la note de Release de Watcher"

releasenotes/source/victoria.rst

@@ -3,4 +3,4 @@ Victoria Series Release Notes
 =============================
 
 .. release-notes::
-   :branch: stable/victoria
+   :branch: unmaintained/victoria

releasenotes/source/wallaby.rst

@@ -3,4 +3,4 @@ Wallaby Series Release Notes
 ============================
 
 .. release-notes::
-   :branch: stable/wallaby
+   :branch: unmaintained/wallaby

releasenotes/source/xena.rst

@@ -3,4 +3,4 @@ Xena Series Release Notes
 =========================
 
 .. release-notes::
-   :branch: stable/xena
+   :branch: unmaintained/xena

releasenotes/source/yoga.rst

@@ -3,4 +3,4 @@ Yoga Series Release Notes
 =========================
 
 .. release-notes::
-   :branch: stable/yoga
+   :branch: unmaintained/yoga

releasenotes/source/zed.rst

@@ -3,4 +3,4 @@ Zed Series Release Notes
 ========================
 
 .. release-notes::
-   :branch: stable/zed
+   :branch: unmaintained/zed

requirements.txt

@@ -1,8 +1,8 @@
-#  The order of packages is significant, because pip processes them in the order
+# Requirements lower bounds listed here are our best effort to keep them up to
-# of appearance. Changing the order has an impact on the overall integration
+# date but we do not test them so no guarantee of having them all correct. If
-# process, which may cause wedges in the gate later.
+# you find any incorrect lower bounds, let us know or propose a fix.
-
 apscheduler>=3.5.1 # MIT License
+eventlet>=0.27.0 # MIT
 jsonpatch>=1.21 # BSD
 keystoneauth1>=3.4.0 # Apache-2.0
 jsonschema>=3.2.0 # MIT
@@ -17,13 +17,13 @@ oslo.context>=2.21.0 # Apache-2.0
 oslo.db>=4.44.0 # Apache-2.0
 oslo.i18n>=3.20.0 # Apache-2.0
 oslo.log>=3.37.0 # Apache-2.0
-oslo.messaging>=8.1.2 # Apache-2.0
+oslo.messaging>=14.1.0 # Apache-2.0
-oslo.policy>=3.6.0 # Apache-2.0
+oslo.policy>=4.5.0 # Apache-2.0
 oslo.reports>=1.27.0 # Apache-2.0
 oslo.serialization>=2.25.0 # Apache-2.0
 oslo.service>=1.30.0 # Apache-2.0
 oslo.upgradecheck>=1.3.0 # Apache-2.0
-oslo.utils>=3.36.0 # Apache-2.0
+oslo.utils>=7.0.0 # Apache-2.0
 oslo.versionedobjects>=1.32.0 # Apache-2.0
 PasteDeploy>=1.5.2 # MIT
 pbr>=3.1.1 # Apache-2.0
@@ -36,6 +36,7 @@ python-keystoneclient>=3.15.0 # Apache-2.0
 python-monascaclient>=1.12.0 # Apache-2.0
 python-neutronclient>=6.7.0 # Apache-2.0
 python-novaclient>=14.1.0 # Apache-2.0
+python-observabilityclient>=0.3.0 # Apache-2.0
 python-openstackclient>=3.14.0 # Apache-2.0
 python-ironicclient>=2.5.0 # Apache-2.0
 SQLAlchemy>=1.2.5 # MIT

setup.cfg

@@ -6,7 +6,7 @@ description_file =
 author = OpenStack
 author_email = openstack-discuss@lists.openstack.org
 home_page = https://docs.openstack.org/watcher/latest/
-python_requires = >=3.6
+python_requires = >=3.9
 classifier =
     Environment :: OpenStack
     Intended Audience :: Information Technology
@@ -17,9 +17,10 @@ classifier =
     Programming Language :: Python :: Implementation :: CPython
     Programming Language :: Python :: 3 :: Only
     Programming Language :: Python :: 3
-    Programming Language :: Python :: 3.6
+    Programming Language :: Python :: 3.9
-    Programming Language :: Python :: 3.7
+    Programming Language :: Python :: 3.10
-    Programming Language :: Python :: 3.8
+    Programming Language :: Python :: 3.11
+    Programming Language :: Python :: 3.12
 
 [files]
 packages =
@@ -108,3 +109,8 @@ watcher_cluster_data_model_collectors =
     compute = watcher.decision_engine.model.collector.nova:NovaClusterDataModelCollector
     storage = watcher.decision_engine.model.collector.cinder:CinderClusterDataModelCollector
     baremetal = watcher.decision_engine.model.collector.ironic:BaremetalClusterDataModelCollector
+
+[codespell]
+skip = *.po,*.js,*.css,*.html,*.svg,HACKING.py,*hacking*,*build*,*_static*,doc/dictionary.txt,*.pyc,*.inv,*.gz,*.jpg,*.png,*.vsd,*.graffle,*.json
+count =
+quiet-level = 4

test-requirements.txt

@@ -1,15 +1,7 @@
-# The order of packages is significant, because pip processes them in the order
-# of appearance. Changing the order has an impact on the overall integration
-# process, which may cause wedges in the gate later.
-
 coverage>=4.5.1 # Apache-2.0
-doc8>=0.8.0 # Apache-2.0
 freezegun>=0.3.10 # Apache-2.0
-hacking>=3.0.1,<3.1.0 # Apache-2.0
 oslotest>=3.3.0 # Apache-2.0
 testscenarios>=0.5.0 # Apache-2.0/BSD
 testtools>=2.3.0 # MIT
 stestr>=2.0.0 # Apache-2.0
-os-api-ref>=1.4.0 # Apache-2.0
+WebTest>=2.0.27 # MIT
-bandit>=1.6.0 # Apache-2.0
-WebTest>=2.0.27 # MIT

tox.ini

@@ -10,10 +10,15 @@ allowlist_externals = find
                       rm
 install_command = pip install -c{env:TOX_CONSTRAINTS_FILE:https://releases.openstack.org/constraints/upper/master} {opts} {packages}
 setenv =
-   VIRTUAL_ENV={envdir}
+  VIRTUAL_ENV={envdir}
+  OS_STDOUT_CAPTURE=1
+  OS_STDERR_CAPTURE=1
+  OS_TEST_TIMEOUT=30
+  PYTHONDONTWRITEBYTECODE=1
 deps =
     -r{toxinidir}/test-requirements.txt
     -r{toxinidir}/requirements.txt
+    python-libmaas>=0.6.8
 commands =
   rm -f .testrepository/times.dbm
   find . -type f -name "*.py[c|o]" -delete
@@ -25,12 +30,22 @@ passenv =
   HTTPS_PROXY
   no_proxy
   NO_PROXY
+  OS_DEBUG
+  # NOTE(sean-k-mooney) optimization is enabled by default and when enabled
+  # asserts are complied out. Disable optimization to allow asserts in
+  # nova to fire in unit and functional tests. This can be useful for
+  # debugging issue with fixtures and mocks.
+  PYTHONOPTIMIZE
 
 [testenv:pep8]
+description =
+    Run style checks.
+skip_install = true
+deps =
+    pre-commit
 commands =
-    doc8 doc/source/ CONTRIBUTING.rst HACKING.rst README.rst
+    pre-commit run --all-files --show-diff-on-failure
-    flake8
+
-    bandit -r watcher -x watcher/tests/* -n5 -ll -s B320
 
 [testenv:venv]
 setenv = PYTHONHASHSEED=0
@@ -81,7 +96,6 @@ commands =
 commands = python setup.py bdist_wheel
 
 [testenv:pdf-docs]
-envdir = {toxworkdir}/docs
 deps = {[testenv:docs]deps}
 allowlist_externals =
   rm
@@ -96,8 +110,10 @@ deps = -r{toxinidir}/doc/requirements.txt
 commands = sphinx-build -a -W -E -d releasenotes/build/doctrees --keep-going -b html releasenotes/source releasenotes/build/html
 
 [testenv:bandit]
-deps = -r{toxinidir}/test-requirements.txt
+skip_install = true
-commands = bandit -r watcher -x watcher/tests/* -n5 -ll -s B320
+deps = {[testenv:pep8]deps}
+commands =
+    pre-commit run --all-files --show-diff-on-failure bandit
 
 [flake8]
 filename = *.py,app.wsgi

watcher/api/controllers/v1/action.py

@@ -55,9 +55,8 @@ possible to :ref:`develop new implementations <implement_action_plugin>` which
 are dynamically loaded by Watcher at launch time.
 """
 
-import datetime
-
 from http import HTTPStatus
+from oslo_utils import timeutils
 import pecan
 from pecan import rest
 import wsme
@@ -194,9 +193,9 @@ class Action(base.APIBase):
         sample = cls(uuid='27e3153e-d5bf-4b7e-b517-fb518e17f34c',
                      description='action description',
                      state='PENDING',
-                     created_at=datetime.datetime.utcnow(),
+                     created_at=timeutils.utcnow(),
                      deleted_at=None,
-                     updated_at=datetime.datetime.utcnow(),
+                     updated_at=timeutils.utcnow(),
                      parents=[])
         sample._action_plan_uuid = '7ae81bb3-dec3-4289-8d6c-da80bd8001ae'
         return cls._convert_with_links(sample, 'http://localhost:9322', expand)
@@ -230,6 +229,7 @@ class ActionCollection(collection.Collection):
 
 class ActionsController(rest.RestController):
     """REST controller for Actions."""
+
     def __init__(self):
         super(ActionsController, self).__init__()
 
@@ -334,7 +334,7 @@ class ActionsController(rest.RestController):
         policy.enforce(context, 'action:detail',
                        action='action:detail')
 
-        # NOTE(lucasagomes): /detail should only work agaist collections
+        # NOTE(lucasagomes): /detail should only work against collections
         parent = pecan.request.path.split('/')[:-1][-1]
         if parent != "actions":
             raise exception.HTTPNotFound

watcher/api/controllers/v1/action_plan.py

@@ -54,10 +54,9 @@ To see the life-cycle and description of
 state machine <action_plan_state_machine>`.
 """
 
-import datetime
-
 from http import HTTPStatus
 from oslo_log import log
+from oslo_utils import timeutils
 import pecan
 from pecan import rest
 import wsme
@@ -293,9 +292,9 @@ class ActionPlan(base.APIBase):
     def sample(cls, expand=True):
         sample = cls(uuid='9ef4d84c-41e8-4418-9220-ce55be0436af',
                      state='ONGOING',
-                     created_at=datetime.datetime.utcnow(),
+                     created_at=timeutils.utcnow(),
                      deleted_at=None,
-                     updated_at=datetime.datetime.utcnow())
+                     updated_at=timeutils.utcnow())
         sample._audit_uuid = 'abcee106-14d3-4515-b744-5a26885cf6f6'
         sample._efficacy_indicators = [{'description': 'Test indicator',
                                         'name': 'test_indicator',
@@ -434,7 +433,7 @@ class ActionPlansController(rest.RestController):
         policy.enforce(context, 'action_plan:detail',
                        action='action_plan:detail')
 
-        # NOTE(lucasagomes): /detail should only work agaist collections
+        # NOTE(lucasagomes): /detail should only work against collections
         parent = pecan.request.path.split('/')[:-1][-1]
         if parent != "action_plans":
             raise exception.HTTPNotFound

watcher/api/controllers/v1/audit.py

@@ -33,6 +33,8 @@ import datetime
 from dateutil import tz
 
 from http import HTTPStatus
+from oslo_log import log
+from oslo_utils import timeutils
 import pecan
 from pecan import rest
 import wsme
@@ -40,8 +42,6 @@ from wsme import types as wtypes
 from wsme import utils as wutils
 import wsmeext.pecan as wsme_pecan
 
-from oslo_log import log
-
 from watcher._i18n import _
 from watcher.api.controllers import base
 from watcher.api.controllers import link
@@ -171,16 +171,16 @@ class AuditPostType(wtypes.Base):
                 strategy = _get_object_by_value(context, objects.Strategy,
                                                 self.strategy)
                 self.name = "%s-%s" % (strategy.name,
-                                       datetime.datetime.utcnow().isoformat())
+                                       timeutils.utcnow().isoformat())
             elif self.audit_template_uuid:
                 audit_template = objects.AuditTemplate.get(
                     context, self.audit_template_uuid)
                 self.name = "%s-%s" % (audit_template.name,
-                                       datetime.datetime.utcnow().isoformat())
+                                       timeutils.utcnow().isoformat())
             else:
                 goal = _get_object_by_value(context, objects.Goal, self.goal)
                 self.name = "%s-%s" % (goal.name,
-                                       datetime.datetime.utcnow().isoformat())
+                                       timeutils.utcnow().isoformat())
         # No more than 63 characters
         if len(self.name) > 63:
             LOG.warning("Audit: %s length exceeds 63 characters",
@@ -424,15 +424,15 @@ class Audit(base.APIBase):
                      name='My Audit',
                      audit_type='ONESHOT',
                      state='PENDING',
-                     created_at=datetime.datetime.utcnow(),
+                     created_at=timeutils.utcnow(),
                      deleted_at=None,
-                     updated_at=datetime.datetime.utcnow(),
+                     updated_at=timeutils.utcnow(),
                      interval='7200',
                      scope=[],
                      auto_trigger=False,
-                     next_run_time=datetime.datetime.utcnow(),
+                     next_run_time=timeutils.utcnow(),
-                     start_time=datetime.datetime.utcnow(),
+                     start_time=timeutils.utcnow(),
-                     end_time=datetime.datetime.utcnow())
+                     end_time=timeutils.utcnow())
 
         sample.goal_id = '7ae81bb3-dec3-4289-8d6c-da80bd8001ae'
         sample.strategy_id = '7ae81bb3-dec3-4289-8d6c-da80bd8001ff'
@@ -468,6 +468,7 @@ class AuditCollection(collection.Collection):
 
 class AuditsController(rest.RestController):
     """REST controller for Audits."""
+
     def __init__(self):
         super(AuditsController, self).__init__()
         self.dc_client = rpcapi.DecisionEngineAPI()
@@ -569,7 +570,7 @@ class AuditsController(rest.RestController):
         context = pecan.request.context
         policy.enforce(context, 'audit:detail',
                        action='audit:detail')
-        # NOTE(lucasagomes): /detail should only work agaist collections
+        # NOTE(lucasagomes): /detail should only work against collections
         parent = pecan.request.path.split('/')[:-1][-1]
         if parent != "audits":
             raise exception.HTTPNotFound

watcher/api/controllers/v1/audit_template.py

@@ -43,9 +43,8 @@ will be launched automatically or will need a manual confirmation from the
 :ref:`Administrator <administrator_definition>`.
 """
 
-import datetime
-
 from http import HTTPStatus
+from oslo_utils import timeutils
 import pecan
 from pecan import rest
 import wsme
@@ -440,9 +439,9 @@ class AuditTemplate(base.APIBase):
                      description='Description of my audit template',
                      goal_uuid='83e44733-b640-40e2-8d8a-7dd3be7134e6',
                      strategy_uuid='367d826e-b6a4-4b70-bc44-c3f6fe1c9986',
-                     created_at=datetime.datetime.utcnow(),
+                     created_at=timeutils.utcnow(),
                      deleted_at=None,
-                     updated_at=datetime.datetime.utcnow(),
+                     updated_at=timeutils.utcnow(),
                      scope=[],)
         return cls._convert_with_links(sample, 'http://localhost:9322', expand)
 
@@ -476,6 +475,7 @@ class AuditTemplateCollection(collection.Collection):
 
 class AuditTemplatesController(rest.RestController):
     """REST controller for AuditTemplates."""
+
     def __init__(self):
         super(AuditTemplatesController, self).__init__()
 
@@ -576,7 +576,7 @@ class AuditTemplatesController(rest.RestController):
         policy.enforce(context, 'audit_template:detail',
                        action='audit_template:detail')
 
-        # NOTE(lucasagomes): /detail should only work agaist collections
+        # NOTE(lucasagomes): /detail should only work against collections
         parent = pecan.request.path.split('/')[:-1][-1]
         if parent != "audit_templates":
             raise exception.HTTPNotFound

watcher/api/controllers/v1/data_model.py

@@ -32,6 +32,7 @@ from watcher.decision_engine import rpcapi
 
 class DataModelController(rest.RestController):
     """REST controller for data model"""
+
     def __init__(self):
         super(DataModelController, self).__init__()
 

watcher/api/controllers/v1/goal.py

@@ -24,7 +24,7 @@ Here are some examples of :ref:`Goals <goal_definition>`:
 -  minimize the energy consumption
 -  minimize the number of compute nodes (consolidation)
 -  balance the workload among compute nodes
--  minimize the license cost (some softwares have a licensing model which is
+-  minimize the license cost (some software have a licensing model which is
    based on the number of sockets or cores where the software is deployed)
 -  find the most appropriate moment for a planned maintenance on a
    given group of host (which may be an entire availability zone):
@@ -153,6 +153,7 @@ class GoalCollection(collection.Collection):
 
 class GoalsController(rest.RestController):
     """REST controller for Goals."""
+
     def __init__(self):
         super(GoalsController, self).__init__()
 
@@ -216,7 +217,7 @@ class GoalsController(rest.RestController):
         context = pecan.request.context
         policy.enforce(context, 'goal:detail',
                        action='goal:detail')
-        # NOTE(lucasagomes): /detail should only work agaist collections
+        # NOTE(lucasagomes): /detail should only work against collections
         parent = pecan.request.path.split('/')[:-1][-1]
         if parent != "goals":
             raise exception.HTTPNotFound

watcher/api/controllers/v1/scoring_engine.py

@@ -145,6 +145,7 @@ class ScoringEngineCollection(collection.Collection):
 
 class ScoringEngineController(rest.RestController):
     """REST controller for Scoring Engines."""
+
     def __init__(self):
         super(ScoringEngineController, self).__init__()
 

watcher/api/controllers/v1/service.py

@@ -175,6 +175,7 @@ class ServiceCollection(collection.Collection):
 
 class ServicesController(rest.RestController):
     """REST controller for Services."""
+
     def __init__(self):
         super(ServicesController, self).__init__()
 
@@ -236,7 +237,7 @@ class ServicesController(rest.RestController):
         context = pecan.request.context
         policy.enforce(context, 'service:detail',
                        action='service:detail')
-        # NOTE(lucasagomes): /detail should only work agaist collections
+        # NOTE(lucasagomes): /detail should only work against collections
         parent = pecan.request.path.split('/')[:-1][-1]
         if parent != "services":
             raise exception.HTTPNotFound

watcher/api/controllers/v1/strategy.py

@@ -196,6 +196,7 @@ class StrategyCollection(collection.Collection):
 
 class StrategiesController(rest.RestController):
     """REST controller for Strategies."""
+
     def __init__(self):
         super(StrategiesController, self).__init__()
 
@@ -283,7 +284,7 @@ class StrategiesController(rest.RestController):
         context = pecan.request.context
         policy.enforce(context, 'strategy:detail',
                        action='strategy:detail')
-        # NOTE(lucasagomes): /detail should only work agaist collections
+        # NOTE(lucasagomes): /detail should only work against collections
         parent = pecan.request.path.split('/')[:-1][-1]
         if parent != "strategies":
             raise exception.HTTPNotFound

watcher/api/controllers/v1/types.py

@@ -161,6 +161,7 @@ class MultiType(wtypes.UserType):
     :param types: Variable-length list of types.
 
     """
+
     def __init__(self, *types):
         self.types = types
 

watcher/api/controllers/v1/webhooks.py

@@ -32,6 +32,7 @@ LOG = log.getLogger(__name__)
 
 class WebhookController(rest.RestController):
     """REST controller for webhooks resource."""
+
     def __init__(self):
         super(WebhookController, self).__init__()
         self.dc_client = rpcapi.DecisionEngineAPI()

watcher/api/hooks.py

@@ -83,6 +83,7 @@ class NoExceptionTracebackHook(hooks.PecanHook):
     # 'on_error' never fired for wsme+pecan pair. wsme @wsexpose decorator
     # catches and handles all the errors, so 'on_error' dedicated for unhandled
     # exceptions never fired.
+
     def after(self, state):
         # Omit empty body. Some errors may not have body at this level yet.
         if not state.response.body:

watcher/api/middleware/auth_token.py

@@ -33,6 +33,7 @@ class AuthTokenMiddleware(auth_token.AuthProtocol):
     for public routes in the API.
 
     """
+
     def __init__(self, app, conf, public_api_routes=()):
         route_pattern_tpl = r'%s(\.json|\.xml)?$'
 

watcher/applier/actions/base.py

@@ -118,7 +118,8 @@ class BaseAction(loadable.Loadable, metaclass=abc.ABCMeta):
         """
         raise NotImplementedError()
 
-    @abc.abstractproperty
+    @property
+    @abc.abstractmethod
     def schema(self):
         """Defines a Schema that the input parameters shall comply to
 

watcher/applier/actions/change_node_power_state.py

@@ -17,17 +17,17 @@
 # limitations under the License.
 #
 
-import enum
 import time
 
+from oslo_log import log
+
 from watcher._i18n import _
 from watcher.applier.actions import base
 from watcher.common import exception
+from watcher.common.metal_helper import constants as metal_constants
+from watcher.common.metal_helper import factory as metal_helper_factory
 
-
+LOG = log.getLogger(__name__)
-class NodeState(enum.Enum):
-    POWERON = 'on'
-    POWEROFF = 'off'
 
 
 class ChangeNodePowerState(base.BaseAction):
@@ -43,8 +43,8 @@ class ChangeNodePowerState(base.BaseAction):
          'state': str,
         })
 
-    The `resource_id` references a ironic node id (list of available
+    The `resource_id` references a baremetal node id (list of available
-    ironic node is returned by this command: ``ironic node-list``).
+    ironic nodes is returned by this command: ``ironic node-list``).
     The `state` value should either be `on` or `off`.
     """
 
@@ -59,10 +59,14 @@ class ChangeNodePowerState(base.BaseAction):
                     'type': 'string',
                     "minlength": 1
                 },
+                'resource_name': {
+                    'type': 'string',
+                    "minlength": 1
+                },
                 'state': {
                     'type': 'string',
-                    'enum': [NodeState.POWERON.value,
+                    'enum': [metal_constants.PowerState.ON.value,
-                             NodeState.POWEROFF.value]
+                             metal_constants.PowerState.OFF.value]
                 }
             },
             'required': ['resource_id', 'state'],
@@ -82,10 +86,10 @@ class ChangeNodePowerState(base.BaseAction):
         return self._node_manage_power(target_state)
 
     def revert(self):
-        if self.state == NodeState.POWERON.value:
+        if self.state == metal_constants.PowerState.ON.value:
-            target_state = NodeState.POWEROFF.value
+            target_state = metal_constants.PowerState.OFF.value
-        elif self.state == NodeState.POWEROFF.value:
+        elif self.state == metal_constants.PowerState.OFF.value:
-            target_state = NodeState.POWERON.value
+            target_state = metal_constants.PowerState.ON.value
         return self._node_manage_power(target_state)
 
     def _node_manage_power(self, state, retry=60):
@@ -93,30 +97,32 @@ class ChangeNodePowerState(base.BaseAction):
             raise exception.IllegalArgumentException(
                 message=_("The target state is not defined"))
 
-        ironic_client = self.osc.ironic()
+        metal_helper = metal_helper_factory.get_helper(self.osc)
-        nova_client = self.osc.nova()
+        node = metal_helper.get_node(self.node_uuid)
-        current_state = ironic_client.node.get(self.node_uuid).power_state
+        current_state = node.get_power_state()
-        # power state: 'power on' or 'power off', if current node state
+
-        # is the same as state, just return True
+        if state == current_state.value:
-        if state in current_state:
             return True
 
-        if state == NodeState.POWEROFF.value:
+        if state == metal_constants.PowerState.OFF.value:
-            node_info = ironic_client.node.get(self.node_uuid).to_dict()
+            compute_node = node.get_hypervisor_node().to_dict()
-            compute_node_id = node_info['extra']['compute_node_id']
-            compute_node = nova_client.hypervisors.get(compute_node_id)
-            compute_node = compute_node.to_dict()
             if (compute_node['running_vms'] == 0):
-                ironic_client.node.set_power_state(
+                node.set_power_state(state)
-                    self.node_uuid, state)
+            else:
+                LOG.warning(
+                    "Compute node %s has %s running vms and will "
+                    "NOT be shut off.",
+                    compute_node["hypervisor_hostname"],
+                    compute_node['running_vms'])
+                return False
         else:
-            ironic_client.node.set_power_state(self.node_uuid, state)
+            node.set_power_state(state)
 
-        ironic_node = ironic_client.node.get(self.node_uuid)
+        node = metal_helper.get_node(self.node_uuid)
-        while ironic_node.power_state == current_state and retry:
+        while node.get_power_state() == current_state and retry:
             time.sleep(10)
             retry -= 1
-            ironic_node = ironic_client.node.get(self.node_uuid)
+            node = metal_helper.get_node(self.node_uuid)
         if retry > 0:
             return True
         else:
@@ -130,4 +136,4 @@ class ChangeNodePowerState(base.BaseAction):
 
     def get_description(self):
         """Description of the action"""
-        return ("Compute node power on/off through ironic.")
+        return ("Compute node power on/off through Ironic or MaaS.")

watcher/applier/workflow_engine/default.py

@@ -199,5 +199,6 @@ class TaskFlowNop(flow_task.Task):
 
     We need at least two atoms to create a link.
     """
+
     def execute(self):
         pass

watcher/cmd/__init__.py

@@ -15,13 +15,15 @@
 # common/service.py.  This allows the API service to run without monkey
 # patching under Apache (which uses its own concurrency model). Mixing
 # concurrency models can cause undefined behavior and potentially API timeouts.
-import eventlet
+# NOTE(sean-k-mooney) while ^ is true, since that was written asyncio was added
-
+# to the code base in addition to apscheduler which provides native threads.
-eventlet.monkey_patch()
+# As such we have a lot of technical debt to fix with regards to watchers
-
+# concurrency model as we are mixing up to 3 models the same process.
-# Monkey patch the original current_thread to use the up-to-date _active
+# apscheduler does not technically support eventlet but it has mostly worked
-# global variable. See https://bugs.launchpad.net/bugs/1863021 and
+# until now, apscheduler is used to provide a job schedulers which mixes
-# https://github.com/eventlet/eventlet/issues/592
+# monkey patched and non monkey patched code in the same process.
-import __original_module_threading as orig_threading  # noqa
+# That is problematic and can lead to errors on python 3.12+.
-import threading  # noqa
+# The maas support added asyncio to the codebase which is unsafe to mix
-orig_threading.current_thread.__globals__['_active'] = threading._active
+# with eventlets by default.
+from watcher import eventlet
+eventlet.patch()

watcher/common/cinder_helper.py

@@ -153,7 +153,7 @@ class CinderHelper(object):
         final_status = ('success', 'error')
         while getattr(volume, 'migration_status') not in final_status:
             volume = self.get_volume(volume.id)
-            LOG.debug('Waiting the migration of {0}'.format(volume))
+            LOG.debug('Waiting the migration of %s', volume)
             time.sleep(retry_interval)
             if getattr(volume, 'migration_status') == 'error':
                 host_name = getattr(volume, 'os-vol-host-attr:host')
@@ -230,7 +230,7 @@ class CinderHelper(object):
             availability_zone=getattr(volume, 'availability_zone'))
         while getattr(new_volume, 'status') != 'available' and retry:
             new_volume = cinder.volumes.get(new_volume.id)
-            LOG.debug('Waiting volume creation of {0}'.format(new_volume))
+            LOG.debug('Waiting volume creation of %s', new_volume)
             time.sleep(retry_interval)
             retry -= 1
             LOG.debug("retry count: %s", retry)

watcher/common/clients.py

@@ -25,12 +25,13 @@ from novaclient import api_versions as nova_api_versions
 from novaclient import client as nvclient
 
 from watcher.common import exception
+from watcher.common import utils
 
 try:
-    from ceilometerclient import client as ceclient
+    from maas import client as maas_client
-    HAS_CEILCLIENT = True
 except ImportError:
-    HAS_CEILCLIENT = False
+    maas_client = None
+
 
 CONF = cfg.CONF
 
@@ -70,10 +71,10 @@ class OpenStackClients(object):
         self._glance = None
         self._gnocchi = None
         self._cinder = None
-        self._ceilometer = None
         self._monasca = None
         self._neutron = None
         self._ironic = None
+        self._maas = None
         self._placement = None
 
     def _get_keystone_session(self):
@@ -180,24 +181,6 @@ class OpenStackClients(object):
                                        session=self.session)
         return self._cinder
 
-    @exception.wrap_keystone_exception
-    def ceilometer(self):
-        if self._ceilometer:
-            return self._ceilometer
-
-        ceilometerclient_version = self._get_client_option('ceilometer',
-                                                           'api_version')
-        ceilometer_endpoint_type = self._get_client_option('ceilometer',
-                                                           'endpoint_type')
-        ceilometer_region_name = self._get_client_option('ceilometer',
-                                                         'region_name')
-        self._ceilometer = ceclient.get_client(
-            ceilometerclient_version,
-            endpoint_type=ceilometer_endpoint_type,
-            region_name=ceilometer_region_name,
-            session=self.session)
-        return self._ceilometer
-
     @exception.wrap_keystone_exception
     def monasca(self):
         if self._monasca:
@@ -265,6 +248,23 @@ class OpenStackClients(object):
                                            session=self.session)
         return self._ironic
 
+    def maas(self):
+        if self._maas:
+            return self._maas
+
+        if not maas_client:
+            raise exception.UnsupportedError(
+                "MAAS client unavailable. Please install python-libmaas.")
+
+        url = self._get_client_option('maas', 'url')
+        api_key = self._get_client_option('maas', 'api_key')
+        timeout = self._get_client_option('maas', 'timeout')
+        self._maas = utils.async_compat_call(
+            maas_client.connect,
+            url, apikey=api_key,
+            timeout=timeout)
+        return self._maas
+
     @exception.wrap_keystone_exception
     def placement(self):
         if self._placement:

watcher/common/context.py

@@ -11,12 +11,15 @@
 # under the License.
 
 from oslo_context import context
+from oslo_db.sqlalchemy import enginefacade
 from oslo_log import log
 from oslo_utils import timeutils
 
+
 LOG = log.getLogger(__name__)
 
 
+@enginefacade.transaction_context_provider
 class RequestContext(context.RequestContext):
     """Extends security contexts from the OpenStack common library."""
 

watcher/common/exception.py

@@ -154,6 +154,10 @@ class InvalidParameter(Invalid):
     msg_fmt = _("%(parameter)s has to be of type %(parameter_type)s")
 
 
+class MissingParameter(Invalid):
+    msg_fmt = _("%(parameter)s is required but missing. Check watcher.conf")
+
+
 class InvalidIdentity(Invalid):
     msg_fmt = _("Expected a uuid or int but received %(identity)s")
 

watcher/common/keystone_helper.py

@@ -72,8 +72,8 @@ class KeystoneHelper(object):
                     message=(_("Project not Found: %s") % name_or_id))
             if len(projects) > 1:
                 raise exception.Invalid(
-                    messsage=(_("Project name seems ambiguous: %s") %
+                    message=(_("Project name seems ambiguous: %s") %
-                              name_or_id))
+                             name_or_id))
             return projects[0]
 
     def get_domain(self, name_or_id):

watcher/common/metal_helper/base.py

@@ -0,0 +1,81 @@
+# Copyright 2023 Cloudbase Solutions
+# All Rights Reserved.
+#
+#    Licensed under the Apache License, Version 2.0 (the "License"); you may
+#    not use this file except in compliance with the License. You may obtain
+#    a copy of the License at
+#
+#         http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
+#    WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
+#    License for the specific language governing permissions and limitations
+#    under the License.
+
+import abc
+
+from watcher.common import exception
+from watcher.common.metal_helper import constants as metal_constants
+
+
+class BaseMetalNode(abc.ABC):
+    hv_up_when_powered_off = False
+
+    def __init__(self, nova_node=None):
+        self._nova_node = nova_node
+
+    def get_hypervisor_node(self):
+        if not self._nova_node:
+            raise exception.Invalid(message="No associated hypervisor.")
+        return self._nova_node
+
+    def get_hypervisor_hostname(self):
+        return self.get_hypervisor_node().hypervisor_hostname
+
+    @abc.abstractmethod
+    def get_power_state(self):
+        # TODO(lpetrut): document the following methods
+        pass
+
+    @abc.abstractmethod
+    def get_id(self):
+        """Return the node id provided by the bare metal service."""
+        pass
+
+    @abc.abstractmethod
+    def power_on(self):
+        pass
+
+    @abc.abstractmethod
+    def power_off(self):
+        pass
+
+    def set_power_state(self, state):
+        state = metal_constants.PowerState(state)
+        if state == metal_constants.PowerState.ON:
+            self.power_on()
+        elif state == metal_constants.PowerState.OFF:
+            self.power_off()
+        else:
+            raise exception.UnsupportedActionType(
+                "Cannot set power state: %s" % state)
+
+
+class BaseMetalHelper(abc.ABC):
+    def __init__(self, osc):
+        self._osc = osc
+
+    @property
+    def nova_client(self):
+        if not getattr(self, "_nova_client", None):
+            self._nova_client = self._osc.nova()
+        return self._nova_client
+
+    @abc.abstractmethod
+    def list_compute_nodes(self):
+        pass
+
+    @abc.abstractmethod
+    def get_node(self, node_id):
+        pass

watcher/common/metal_helper/constants.py

@@ -0,0 +1,23 @@
+# Copyright 2023 Cloudbase Solutions
+# All Rights Reserved.
+#
+#    Licensed under the Apache License, Version 2.0 (the "License"); you may
+#    not use this file except in compliance with the License. You may obtain
+#    a copy of the License at
+#
+#         http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
+#    WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
+#    License for the specific language governing permissions and limitations
+#    under the License.
+
+import enum
+
+
+class PowerState(str, enum.Enum):
+    ON = "on"
+    OFF = "off"
+    UNKNOWN = "unknown"
+    ERROR = "error"

watcher/common/metal_helper/factory.py

@@ -0,0 +1,33 @@
+# Copyright 2023 Cloudbase Solutions
+# All Rights Reserved.
+#
+#    Licensed under the Apache License, Version 2.0 (the "License"); you may
+#    not use this file except in compliance with the License. You may obtain
+#    a copy of the License at
+#
+#         http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
+#    WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
+#    License for the specific language governing permissions and limitations
+#    under the License.
+
+from oslo_config import cfg
+
+from watcher.common import clients
+from watcher.common.metal_helper import ironic
+from watcher.common.metal_helper import maas
+
+CONF = cfg.CONF
+
+
+def get_helper(osc=None):
+    # TODO(lpetrut): consider caching this client.
+    if not osc:
+        osc = clients.OpenStackClients()
+
+    if CONF.maas_client.url:
+        return maas.MaasHelper(osc)
+    else:
+        return ironic.IronicHelper(osc)

watcher/common/metal_helper/ironic.py

@@ -0,0 +1,94 @@
+# Copyright 2023 Cloudbase Solutions
+# All Rights Reserved.
+#
+#    Licensed under the Apache License, Version 2.0 (the "License"); you may
+#    not use this file except in compliance with the License. You may obtain
+#    a copy of the License at
+#
+#         http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
+#    WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
+#    License for the specific language governing permissions and limitations
+#    under the License.
+
+from oslo_log import log
+
+from watcher.common.metal_helper import base
+from watcher.common.metal_helper import constants as metal_constants
+
+LOG = log.getLogger(__name__)
+
+POWER_STATES_MAP = {
+    'power on': metal_constants.PowerState.ON,
+    'power off': metal_constants.PowerState.OFF,
+    # For now, we only use ON/OFF states
+    'rebooting': metal_constants.PowerState.ON,
+    'soft power off': metal_constants.PowerState.OFF,
+    'soft reboot': metal_constants.PowerState.ON,
+}
+
+
+class IronicNode(base.BaseMetalNode):
+    hv_up_when_powered_off = True
+
+    def __init__(self, ironic_node, nova_node, ironic_client):
+        super().__init__(nova_node)
+
+        self._ironic_client = ironic_client
+        self._ironic_node = ironic_node
+
+    def get_power_state(self):
+        return POWER_STATES_MAP.get(self._ironic_node.power_state,
+                                    metal_constants.PowerState.UNKNOWN)
+
+    def get_id(self):
+        return self._ironic_node.uuid
+
+    def power_on(self):
+        self._ironic_client.node.set_power_state(self.get_id(), "on")
+
+    def power_off(self):
+        self._ironic_client.node.set_power_state(self.get_id(), "off")
+
+
+class IronicHelper(base.BaseMetalHelper):
+    @property
+    def _client(self):
+        if not getattr(self, "_cached_client", None):
+            self._cached_client = self._osc.ironic()
+        return self._cached_client
+
+    def list_compute_nodes(self):
+        out_list = []
+        # TODO(lpetrut): consider using "detailed=True" instead of making
+        # an additional GET request per node
+        node_list = self._client.node.list()
+
+        for node in node_list:
+            node_info = self._client.node.get(node.uuid)
+            hypervisor_id = node_info.extra.get('compute_node_id', None)
+            if hypervisor_id is None:
+                LOG.warning('Cannot find compute_node_id in extra '
+                            'of ironic node %s', node.uuid)
+                continue
+
+            hypervisor_node = self.nova_client.hypervisors.get(hypervisor_id)
+            if hypervisor_node is None:
+                LOG.warning('Cannot find hypervisor %s', hypervisor_id)
+                continue
+
+            out_node = IronicNode(node, hypervisor_node, self._client)
+            out_list.append(out_node)
+
+        return out_list
+
+    def get_node(self, node_id):
+        ironic_node = self._client.node.get(node_id)
+        compute_node_id = ironic_node.extra.get('compute_node_id')
+        if compute_node_id:
+            compute_node = self.nova_client.hypervisors.get(compute_node_id)
+        else:
+            compute_node = None
+        return IronicNode(ironic_node, compute_node, self._client)

watcher/common/metal_helper/maas.py

@@ -0,0 +1,125 @@
+# Copyright 2023 Cloudbase Solutions
+# All Rights Reserved.
+#
+#    Licensed under the Apache License, Version 2.0 (the "License"); you may
+#    not use this file except in compliance with the License. You may obtain
+#    a copy of the License at
+#
+#         http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
+#    WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
+#    License for the specific language governing permissions and limitations
+#    under the License.
+
+from oslo_config import cfg
+from oslo_log import log
+
+from watcher.common import exception
+from watcher.common.metal_helper import base
+from watcher.common.metal_helper import constants as metal_constants
+from watcher.common import utils
+
+CONF = cfg.CONF
+LOG = log.getLogger(__name__)
+
+try:
+    from maas.client import enum as maas_enum
+except ImportError:
+    maas_enum = None
+
+
+class MaasNode(base.BaseMetalNode):
+    hv_up_when_powered_off = False
+
+    def __init__(self, maas_node, nova_node, maas_client):
+        super().__init__(nova_node)
+
+        self._maas_client = maas_client
+        self._maas_node = maas_node
+
+    def get_power_state(self):
+        maas_state = utils.async_compat_call(
+            self._maas_node.query_power_state,
+            timeout=CONF.maas_client.timeout)
+
+        # python-libmaas may not be available, so we'll avoid a global
+        # variable.
+        power_states_map = {
+            maas_enum.PowerState.ON: metal_constants.PowerState.ON,
+            maas_enum.PowerState.OFF: metal_constants.PowerState.OFF,
+            maas_enum.PowerState.ERROR: metal_constants.PowerState.ERROR,
+            maas_enum.PowerState.UNKNOWN: metal_constants.PowerState.UNKNOWN,
+        }
+        return power_states_map.get(maas_state,
+                                    metal_constants.PowerState.UNKNOWN)
+
+    def get_id(self):
+        return self._maas_node.system_id
+
+    def power_on(self):
+        LOG.info("Powering on MAAS node: %s %s",
+                 self._maas_node.fqdn,
+                 self._maas_node.system_id)
+        utils.async_compat_call(
+            self._maas_node.power_on,
+            timeout=CONF.maas_client.timeout)
+
+    def power_off(self):
+        LOG.info("Powering off MAAS node: %s %s",
+                 self._maas_node.fqdn,
+                 self._maas_node.system_id)
+        utils.async_compat_call(
+            self._maas_node.power_off,
+            timeout=CONF.maas_client.timeout)
+
+
+class MaasHelper(base.BaseMetalHelper):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        if not maas_enum:
+            raise exception.UnsupportedError(
+                "MAAS client unavailable. Please install python-libmaas.")
+
+    @property
+    def _client(self):
+        if not getattr(self, "_cached_client", None):
+            self._cached_client = self._osc.maas()
+        return self._cached_client
+
+    def list_compute_nodes(self):
+        out_list = []
+        node_list = utils.async_compat_call(
+            self._client.machines.list,
+            timeout=CONF.maas_client.timeout)
+
+        compute_nodes = self.nova_client.hypervisors.list()
+        compute_node_map = dict()
+        for compute_node in compute_nodes:
+            compute_node_map[compute_node.hypervisor_hostname] = compute_node
+
+        for node in node_list:
+            hypervisor_node = compute_node_map.get(node.fqdn)
+            if not hypervisor_node:
+                LOG.info('Cannot find hypervisor %s', node.fqdn)
+                continue
+
+            out_node = MaasNode(node, hypervisor_node, self._client)
+            out_list.append(out_node)
+
+        return out_list
+
+    def _get_compute_node_by_hostname(self, hostname):
+        compute_nodes = self.nova_client.hypervisors.search(
+            hostname, detailed=True)
+        for compute_node in compute_nodes:
+            if compute_node.hypervisor_hostname == hostname:
+                return compute_node
+
+    def get_node(self, node_id):
+        maas_node = utils.async_compat_call(
+            self._client.machines.get, node_id,
+            timeout=CONF.maas_client.timeout)
+        compute_node = self._get_compute_node_by_hostname(maas_node.fqdn)
+        return MaasNode(maas_node, compute_node, self._client)

watcher/common/nova_helper.py

@@ -292,9 +292,7 @@ class NovaHelper(object):
                       'OS-EXT-STS:vm_state') != 'resized' \
                 and retry:
             instance = self.nova.servers.get(instance.id)
-            LOG.debug(
+            LOG.debug('Waiting the resize of %s to %s', instance, flavor_id)
-                'Waiting the resize of {0}  to {1}'.format(
-                    instance, flavor_id))
             time.sleep(1)
             retry -= 1
 
@@ -349,8 +347,7 @@ class NovaHelper(object):
             if dest_hostname is None:
                 while (instance.status not in ['ACTIVE', 'ERROR'] and retry):
                     instance = self.nova.servers.get(instance.id)
-                    LOG.debug(
+                    LOG.debug('Waiting the migration of %s', instance.id)
-                        'Waiting the migration of {0}'.format(instance.id))
                     time.sleep(1)
                     retry -= 1
                 new_hostname = getattr(instance, 'OS-EXT-SRV-ATTR:host')
@@ -371,11 +368,9 @@ class NovaHelper(object):
                 if not getattr(instance, 'OS-EXT-STS:task_state'):
                     LOG.debug("Instance task state: %s is null", instance_id)
                     break
-                LOG.debug(
+                LOG.debug('Waiting the migration of %s to %s',
-                    'Waiting the migration of {0}  to {1}'.format(
+                          instance,
-                        instance,
+                          getattr(instance, 'OS-EXT-SRV-ATTR:host'))
-                        getattr(instance,
-                                'OS-EXT-SRV-ATTR:host')))
                 time.sleep(1)
                 retry -= 1
 
@@ -725,7 +720,7 @@ class NovaHelper(object):
             instance_id, old_volume.id, new_volume.id)
         while getattr(new_volume, 'status') != 'in-use' and retry:
             new_volume = self.cinder.volumes.get(new_volume.id)
-            LOG.debug('Waiting volume update to {0}'.format(new_volume))
+            LOG.debug('Waiting volume update to %s', new_volume)
             time.sleep(retry_interval)
             retry -= 1
             LOG.debug("retry count: %s", retry)

watcher/common/policy.py

@@ -18,7 +18,6 @@
 import sys
 
 from oslo_config import cfg
-from oslo_policy import opts
 from oslo_policy import policy
 
 from watcher.common import exception
@@ -27,12 +26,6 @@ from watcher.common import policies
 _ENFORCER = None
 CONF = cfg.CONF
 
-# TODO(gmann): Remove setting the default value of config policy_file
-# once oslo_policy change the default value to 'policy.yaml'.
-# https://github.com/openstack/oslo.policy/blob/a626ad12fe5a3abd49d70e3e5b95589d279ab578/oslo_policy/opts.py#L49
-DEFAULT_POLICY_FILE = 'policy.yaml'
-opts.set_defaults(CONF, DEFAULT_POLICY_FILE)
-
 
 # we can get a policy enforcer by this init.
 # oslo policy support change policy rule dynamically.
@@ -71,7 +64,6 @@ def init(policy_file=None, rules=None,
 
 def enforce(context, rule=None, target=None,
             do_raise=True, exc=None, *args, **kwargs):
-
     """Checks authorization of a rule against the target and credentials.
 
         :param dict context: As much information about the user performing the

watcher/common/rpc.py

@@ -121,7 +121,7 @@ class RequestContextSerializer(messaging.Serializer):
 def get_client(target, version_cap=None, serializer=None):
     assert TRANSPORT is not None
     serializer = RequestContextSerializer(serializer)
-    return messaging.RPCClient(
+    return messaging.get_rpc_client(
         TRANSPORT,
         target,
         version_cap=version_cap,

watcher/common/scheduling.py

@@ -16,16 +16,22 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+import eventlet
+
 from apscheduler import events
-from apscheduler.executors.pool import BasePoolExecutor
+from apscheduler.executors import pool as pool_executor
 from apscheduler.schedulers import background
+
 import futurist
+
 from oslo_service import service
 
+from watcher import eventlet as eventlet_helper
+
 job_events = events
 
 
-class GreenThreadPoolExecutor(BasePoolExecutor):
+class GreenThreadPoolExecutor(pool_executor.BasePoolExecutor):
     """Green thread pool
 
     An executor that runs jobs in a green thread pool.
@@ -43,16 +49,25 @@ executors = {
 }
 
 
-class BackgroundSchedulerService(service.ServiceBase,
+class BackgroundSchedulerService(
-                                 background.BackgroundScheduler):
+        service.ServiceBase, background.BackgroundScheduler):
-    def __init__(self, gconfig={}, **options):
+    def __init__(self, gconfig=None, **options):
+        self.should_patch = eventlet_helper.is_patched()
         if options is None:
             options = {'executors': executors}
         else:
             if 'executors' not in options.keys():
                 options['executors'] = executors
-        super(BackgroundSchedulerService, self).__init__(
+        super().__init__(gconfig or {}, **options)
-            gconfig, **options)
+
+    def _main_loop(self):
+        if self.should_patch:
+            # NOTE(sean-k-mooney): is_patched and monkey_patch form
+            # watcher.eventlet check a non thread local variable to early out
+            # as we do not use eventlet_helper.patch() here to ensure
+            # eventlet.monkey_patch() is actually called.
+            eventlet.monkey_patch()
+        super()._main_loop()
 
     def start(self):
         """Start service."""

watcher/common/service.py

@@ -26,6 +26,7 @@ from oslo_reports import guru_meditation_report as gmr
 from oslo_reports import opts as gmr_opts
 from oslo_service import service
 from oslo_service import wsgi
+from oslo_utils import timeutils
 
 from watcher._i18n import _
 from watcher.api import app
@@ -120,7 +121,7 @@ class ServiceHeartbeat(scheduling.BackgroundSchedulerService):
                                    'host': host})
         if watcher_list:
             watcher_service = watcher_list[0]
-            watcher_service.last_seen_up = datetime.datetime.utcnow()
+            watcher_service.last_seen_up = timeutils.utcnow()
             watcher_service.save()
         else:
             watcher_service = objects.Service(self.context)

watcher/common/service_manager.py

@@ -19,30 +19,37 @@ import abc
 
 class ServiceManager(object, metaclass=abc.ABCMeta):
 
-    @abc.abstractproperty
+    @property
+    @abc.abstractmethod
     def service_name(self):
         raise NotImplementedError()
 
-    @abc.abstractproperty
+    @property
+    @abc.abstractmethod
     def api_version(self):
         raise NotImplementedError()
 
-    @abc.abstractproperty
+    @property
+    @abc.abstractmethod
     def publisher_id(self):
         raise NotImplementedError()
 
-    @abc.abstractproperty
+    @property
+    @abc.abstractmethod
     def conductor_topic(self):
         raise NotImplementedError()
 
-    @abc.abstractproperty
+    @property
+    @abc.abstractmethod
     def notification_topics(self):
         raise NotImplementedError()
 
-    @abc.abstractproperty
+    @property
+    @abc.abstractmethod
     def conductor_endpoints(self):
         raise NotImplementedError()
 
-    @abc.abstractproperty
+    @property
+    @abc.abstractmethod
     def notification_endpoints(self):
         raise NotImplementedError()

watcher/common/utils.py

@@ -16,12 +16,16 @@
 
 """Utilities and helper functions."""
 
+import asyncio
 import datetime
+import inspect
 import random
 import re
 import string
 
 from croniter import croniter
+import eventlet
+from eventlet import tpool
 
 from jsonschema import validators
 from oslo_config import cfg
@@ -162,3 +166,37 @@ Draft4Validator = validators.Draft4Validator
 def random_string(n):
     return ''.join([random.choice(
         string.ascii_letters + string.digits) for i in range(n)])
+
+
+# Some clients (e.g. MAAS) use asyncio, which isn't compatible with Eventlet.
+# As a workaround, we're delegating such calls to a native thread.
+def async_compat_call(f, *args, **kwargs):
+    timeout = kwargs.pop('timeout', None)
+
+    async def async_wrapper():
+        ret = f(*args, **kwargs)
+        if inspect.isawaitable(ret):
+            return await asyncio.wait_for(ret, timeout)
+        return ret
+
+    def tpool_wrapper():
+        # This will run in a separate native thread. Ideally, there should be
+        # a single thread permanently running an asyncio loop, but for
+        # convenience we'll use eventlet.tpool, which leverages a thread pool.
+        #
+        # That being considered, we're setting up a temporary asyncio loop to
+        # handle this call.
+        loop = asyncio.new_event_loop()
+        try:
+            asyncio.set_event_loop(loop)
+            return loop.run_until_complete(async_wrapper())
+        finally:
+            loop.close()
+
+    # We'll use eventlet timeouts as an extra precaution and asyncio timeouts
+    # to avoid lingering threads. For consistency, we'll convert eventlet
+    # timeout exceptions to asyncio timeout errors.
+    with eventlet.timeout.Timeout(
+            seconds=timeout,
+            exception=asyncio.TimeoutError("Timeout: %ss" % timeout)):
+        return tpool.execute(tpool_wrapper)

watcher/conf/__init__.py

@@ -21,7 +21,6 @@ from oslo_config import cfg
 
 from watcher.conf import api
 from watcher.conf import applier
-from watcher.conf import ceilometer_client
 from watcher.conf import cinder_client
 from watcher.conf import clients_auth
 from watcher.conf import collector
@@ -35,12 +34,14 @@ from watcher.conf import grafana_client
 from watcher.conf import grafana_translators
 from watcher.conf import ironic_client
 from watcher.conf import keystone_client
+from watcher.conf import maas_client
 from watcher.conf import monasca_client
 from watcher.conf import neutron_client
 from watcher.conf import nova_client
 from watcher.conf import paths
 from watcher.conf import placement_client
 from watcher.conf import planner
+from watcher.conf import prometheus_client
 from watcher.conf import service
 
 CONF = cfg.CONF
@@ -54,6 +55,7 @@ db.register_opts(CONF)
 planner.register_opts(CONF)
 applier.register_opts(CONF)
 decision_engine.register_opts(CONF)
+maas_client.register_opts(CONF)
 monasca_client.register_opts(CONF)
 nova_client.register_opts(CONF)
 glance_client.register_opts(CONF)
@@ -62,9 +64,9 @@ keystone_client.register_opts(CONF)
 grafana_client.register_opts(CONF)
 grafana_translators.register_opts(CONF)
 cinder_client.register_opts(CONF)
-ceilometer_client.register_opts(CONF)
 neutron_client.register_opts(CONF)
 clients_auth.register_opts(CONF)
 ironic_client.register_opts(CONF)
 collector.register_opts(CONF)
 placement_client.register_opts(CONF)
+prometheus_client.register_opts(CONF)